ZenMode

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well past the annotations: deferred execution ('nothing happens on LinkedIn at the moment you call this'), per-person refusal reporting, Nurture rerouting with moved_to_campaign_id, refusal-with-reason when the account is restricted/paused/cooling/off, and the accepted-but-queued case when the daily allowance is spent. These are exactly the behaviors an agent cannot infer from destructiveHint/idempotentHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and count limit, then layered behavior. It's long and the account-state sentence is dense, but every clause carries information an agent needs; little filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description explains the only return value an agent must act on (moved_to_campaign_id) and the refusal semantics. Combined with the execution-delay disclosure, an agent has everything needed to call it and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 67% schema coverage, the description adds the batch ceiling and the URL-addressing rule on top of the schema, and explains what the idempotency key actually guarantees on retry. It doesn't describe the optional per-lead fields (name, title, company, location), which remain undocumented in both places.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource plus the key constraint ('up to 100 people... by LinkedIn profile URL'), and distinguishes itself from create_campaign and remove_leads_from_campaign by framing it as an enrollment rather than a mutation of the campaign itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context: bulk enrollment through the same validation as a dashboard import, with removal/pause/exclusion explicitly carved out as separate operations. It never names the sibling tools (e.g. use remove_leads_from_campaign or set_contact_outreach_state instead), so routing is implied rather than instructed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Exceeds the annotation baseline (readOnlyHint=false, idempotentHint=true) by disclosing that the campaign is ALWAYS created paused regardless of arguments, that nothing is scheduled and nothing happens on LinkedIn at call time, that dashboard-equivalent checks (plan, Sales Navigator, LinkedIn account) run, and that the engine executes later under daily/weekly limits, business hours and pacing. It also states the return value ('Returns the campaign id').

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The critical constraint (created paused, only launch_campaign activates) is front-loaded and the rest is substantive, not filler. The 'nothing scheduled / nothing happens on LinkedIn' idea is stated twice, a minor redundancy that keeps it just under perfect.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter creation tool with no output schema, it covers prerequisites (plan, Sales Navigator, LinkedIn account), the side-effect profile (nothing happens immediately), the returned id, and the follow-up tools needed to make the campaign useful. An agent has everything required to call it correctly and know what comes next.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns an extra point by tying targeting parameters to the workflow — job_titles/search URL vs lead_source 'list' plus add_leads_to_campaign — which the schema does not explain. Daily limit, locations, companies and idempotency are left entirely to the schema, so it falls short of full compensation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Create a new campaign') plus the key distinguishing trait (opens with a connection note, always created paused). It explicitly names the one sibling that can activate it (launch_campaign), so an agent can separate it from launch/resume without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives the routing conditions directly: use job_titles or a LinkedIn/Sales Navigator search URL for searched leads, or lead_source 'list' when the people will be added later with add_leads_to_campaign. It also states that message content is written afterwards via set_campaign_messages, and that only launch_campaign activates — explicit alternatives rather than inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuine value by disclosing the scope of the data returned (account plan, desktop check-in recency, campaign status breakdown, and a fixed 30-day results window), which is meaningful behavioral context that the annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler: the verb and resource lead, and the enumerated contents follow as the qualifier. Every clause maps to actual returned data rather than restating the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly carries the burden of explaining what comes back and does so concretely, including the time window. It omits any note on response format or freshness beyond the desktop check-in detail, but for a read-only zero-parameter summary tool the coverage is close to sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline is 4. There is nothing for the description to clarify on this dimension.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Summarise the ZenMode account this connector is signed in to') and then enumerates exactly what the summary contains: plan, desktop check-in, campaigns by status, and 30-day results. This scope distinguishes it cleanly from the per-campaign siblings (get_campaign, list_campaigns) and the narrower get_desktop_app/get_setup_status tools without needing to name them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes the usage context inferable — it is the account-level overview/rollup — but never states when to prefer it over get_setup_status, get_desktop_app, or get_safety_status, which partially overlap with the check-in data it returns. No explicit when/when-not or alternative routing is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real value by enumerating the response payload (status, daily limit, business hours, stage counts, date-window results) for a tool with no output schema, though it says nothing about permissions or result-size limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with the scope ('one campaign') stated first and the field list following the colon; no filler. The enumeration is long but each item conveys what the caller will receive.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only, two-parameter lookup, the description covers both the required input source and the shape of the return value, which matters since there is no output schema. The only meaningful omission is how it relates to the overlapping targeting sibling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already documented, including the default-30-day window for 'days' and the campaign_id source. The description restates the default window without adding format or edge-case detail, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Show one campaign') and enumerates the returned fields, which cleanly separates it from the bulk list_campaigns. It never names a sibling explicitly, so differentiation is inferred from 'one campaign' rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use or when-not guidance is given. The description does not address the overlap with get_campaign_targeting, which is listed as a sibling and covers one of the same fields ('targeting'), leaving the agent to guess which tool to call.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish the safe read-only, non-destructive profile, so the bar is lower. The description still adds real behavioral value by disclosing the override rule — a search URL takes precedence over locations and industries — which is a data-interpretation quirk an agent would otherwise misread.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One front-loaded sentence with no filler; the field list is dense but each item is informative. Slightly long, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only getter with full schema coverage and no output schema, the description adequately characterizes what is returned, including the override note. The only real gap is not routing the agent away from get_campaign or toward update_campaign_targeting.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single campaign_id parameter is documented in the schema as coming from list_campaigns. The description adds nothing about the parameter, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (show) and resource (campaign targeting) and enumerates the exact fields returned — job titles, locations, industries, companies, and a pasted LinkedIn/Sales Navigator URL. It distinguishes itself from the generic get_campaign implicitly through that content list, but never names a sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied (read a campaign's targeting config) but there is no explicit when-to-use statement, no mention of the write counterpart update_campaign_targeting, and no guidance on when to prefer get_campaign vs this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered structurally. The description adds real behavioral value by disclosing that the payload includes do-not-contact status and how much conversation history exists in each direction, but says nothing about permissions, pagination, or empty-result behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with no filler, and the enumeration is genuinely informative rather than padding. It is slightly list-heavy for one sentence, but every clause earns its place by naming a returned field.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and only one well-documented input, the description carries the burden of explaining the return payload and does so by enumerating the categories of data returned. Coverage is good for a simple read tool; only edge cases such as a nonexistent or inaccessible contact_id are left unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is a single parameter and schema description coverage is 100% — the schema already explains contact_id and even points to search_contacts as the source. The description adds no format, range, or lookup guidance beyond that, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb+resource ("Show one contact") and enumerates exactly what is returned: profile details, campaign, status, outreach state, do-not-contact status, and per-direction conversation history. The singular "one contact" implicitly separates it from the list-style sibling search_contacts, but no sibling is named explicitly, so it stops short of full differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an agent can infer this is the single-record lookup that follows search_contacts (which the schema also references as the id source). There is no explicit when-to-use statement, no condition that selects it over search_contacts or get_conversation, and no exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds genuinely new context beyond the annotations: chronological ordering (oldest first) and the provenance of outbound entries (sent from ZenMode or typed directly on LinkedIn). It does not explain pagination behavior for limit/offset, which would have earned a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Effectively one front-loaded sentence that carries the scope, ordering, and content, plus a two-word safety tag. Efficient and readable; the 'Read-only.' fragment slightly duplicates the readOnlyHint annotation rather than adding new information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only, single-resource fetch with no output schema, the description plus schema covers what the agent needs: what entity, what content, what ordering, and what safety posture. Only the return shape (entry fields) and paging semantics are left implicit, which is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 75%, so most parameters are documented in the schema itself (limit default, direction enum, contact_id provenance). The description contributes nothing about the optional direction filter or paging, so there is no value added over the structured fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Read), resource (LinkedIn conversation history), and scope (one contact, oldest first), which separates it cleanly from get_contact and search_contacts. The parenthetical content description ('what went out... and what they wrote back') further pins down exactly what is returned.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the noun phrase 'conversation history with one contact' and the contact_id requirement, but no sibling is named as an alternative and no when-not-to-use condition is given (e.g., use get_contact for profile fields instead). Adequate but leaves the agent to infer routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the app opens its own browser window for LinkedIn login, requires a LinkedIn email/password, and Google sign-in is unsupported. Minor remaining gap is no note on caching/expiry of the download link.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the return value, then requirements and the setup sequence. The closing sentence about get_setup_status returning next_step.say is arguably about a sibling tool and slightly dilutes focus, though it does orient the agent in the flow.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no parameters and no output schema, the description carries the burden and covers it well: what is returned, that it is required, login constraints, and plan applicability. The one missing piece is how this relates to set_up_desktop_app, leaving a sibling-selection gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters and the schema forbids additional properties, so there is nothing for the description to disambiguate. Baseline of 4 applies; no parameter-level value can be added.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: returns the desktop app download plus a one-line install command for Mac and Windows. Clear what the caller gets. However, it never distinguishes itself from the sibling set_up_desktop_app, which an agent could easily confuse with this tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit context: the app is required because it performs the LinkedIn work, works on every plan, and states the setup sequence (get_setup_status -> start_trial -> get_desktop_app). No exclusion is given relative to the sibling set_up_desktop_app, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial context beyond the readOnly/idempotent annotations: it names the concrete blocking states (LinkedIn-restricted, paused for the week, cooling down, switched off), explains that new work is still accepted while the allowance is exhausted, and states the null-and-note convention for unobservable counts. This is exactly the behavioral disclosure annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the purpose and then enumerates return contents in one dense but waste-free paragraph. The long multi-clause sentence is information-rich rather than padded, though readability of the enumeration could be tighter.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden itself and does so thoroughly, listing what is reported and how unknowns surface (null with a note). Combined with annotations covering the safety profile, an agent has everything needed to call and interpret this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already documents campaign_id, so the baseline is 3. The description adds real meaning by explaining the effect of the parameter ('to judge one campaign's account'), slightly exceeding baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Read') and resource ('ZenMode's own limits say about this account right now') and enumerates the returned facets (new-work allowance, blocking reasons, desktop app status, business hours, call limits). An agent can distinguish it from siblings like get_account_summary or get_setup_status without opening another schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear usage context and explicitly routes the optional parameter ('Pass campaign_id to judge one campaign's account'). It lacks an explicit when-not or a named alternative sibling for the account-level vs campaign-level case, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context: universal applicability across plan states and the fact that it surfaces an actionable next-step string. It does not discuss auth requirements, but for a read-only status endpoint that gap is minor.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the payload contents before the workflow guidance, and every sentence is functional. There is slight redundancy in stating 'the single next step in plain words' and then re-describing next_step.say, though the second mention does supply a useful field name in the absence of an output schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of describing returns and does so by listing the five things it reads plus the next_step.say field. Combined with the explicit call sequence and plan applicability, nothing an agent needs to invoke and act on it is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, which sets the baseline at 4. There is no parameter behavior to clarify, and the description correctly spends its words on scope and sequencing instead.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Read where this ZenMode account is in setup') and enumerates exactly what is returned: plan/trial, desktop app installed/online, LinkedIn sign-in, campaign count, and next step. It is clearly distinguishable from the sibling mutation tools start_trial and get_desktop_app.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit ordering: get_setup_status, then start_trial (no plan yet), then get_desktop_app (once on a plan). It also states the applicability condition, 'works on every plan, including no plan and Novice,' so the agent knows when the tool is valid and which sibling to call next.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description discloses substantial behavior: preflight changes nothing, activation re-checks all conditions, confirm_token is single-use and state-bound, and no LinkedIn contact happens at call time but later through the campaign engine within limits and business hours. It also explains the special unreviewed_ai_warning case. The annotations mark this as destructive and not idempotent, and the description is consistent with that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening is front-loaded and clear, but the description is long and contains noticeable redundancy. The final sentence about the campaign engine working later inside limits, business hours, and pacing largely repeats an earlier sentence about the same behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of an output schema and the complexity of a two-step destructive activation, the description is complete enough for correct invocation. It explains preflight checks, returned summary content, token semantics, invalid-token handling, delayed activation behavior, and the unreviewed AI warning case.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, so the baseline is 3. The description still adds meaningful semantics for confirm_token, including its single-use nature, 10-minute validity, account/campaign/state binding, and rejection conditions. It adds little about idempotency_key beyond the schema, but the token explanation is valuable.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Activate a paused campaign, in two calls.' It clearly explains the preflight/activation split. However, it does not explicitly distinguish this tool from the sibling resume_campaign, so an agent must infer that difference from naming alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear operational guidance: omit confirm_token for preflight, include it to activate, and expect refusal for missing, expired, used, mismatched, or stale tokens. It does not name alternatives such as resume_campaign, so it falls short of explicit when-to-use-this-vs-another guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the default 30-day window and enumerates the metrics returned, which is useful, but says nothing about pagination, result limits, or whether all campaigns are returned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence that states the resource, the returned fields, and the default window with zero filler. Every clause carries information an agent can use.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly compensates by naming the metrics returned (contacts, requests out, accepted, replied, meetings booked), which an agent cannot get from the schema. Minor gaps remain around result size/pagination, but the essentials for calling the tool are present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and both parameters are fully documented, including the enum for status and the 1-365 bounds for days. The description's "default the last 30 days" merely restates the schema's default for days, adding no new meaning, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("List your campaigns") and adds the fields returned (status, daily limit, results), so an agent knows this is a bulk enumeration rather than a single-record fetch. It never names the sibling it must be chosen over (e.g. get_campaign), so differentiation is implicit rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the mention of a date window defaulting to the last 30 days signals "use this to see recent performance," but there is no when-to-use/when-not guidance and no routing to alternatives like get_campaign for a single campaign or get_account_summary for aggregates.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare non-read-only, non-destructive, idempotent; the description adds substantially more: nothing is deleted, the change is reversible, and crucially that no LinkedIn action occurs at call time because the engine processes campaigns later within daily/weekly limits, business hours and pacing. That deferred-effect disclosure is exactly the kind of context an agent cannot infer from structured fields and prevents a wrong assumption that outreach halts immediately.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action, then ordered by what an agent needs: permission, reversibility, timing. Five sentences is slightly longer than needed but each carries distinct information; nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter mutation with annotations and full schema coverage, the description covers reversibility, permission and deferred execution, which is enough to call it correctly. The one loose end is directing re-activation to launch_campaign when resume_campaign is the sibling that exists, which could send an agent down the wrong path.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with campaign_id sourced from list_campaigns and idempotency_key fully explained (pattern, 24-hour replay behavior). The description adds no parameter-level meaning, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Pause a running campaign') that an agent can match to the pause action without opening the schema. It does not, however, distinguish itself from the existing sibling resume_campaign, and instead points at launch_campaign for re-activation, leaving the pause/resume pair undefined.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit permission guidance ('No confirmation is needed: stopping outreach is always allowed'), which tells the agent it can act without asking the user. It also names a route back (launch_campaign), but gives no conditions for choosing pause over other campaign state changes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description adds meaningful behavior beyond them: history is retained, removal is irreversible for that campaign, LinkedIn is untouched at call time, and execution is deferred through the campaign engine subject to daily/weekly limits and pacing. This deferral and irreversibility context is exactly what the annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core destructive action and its concern are front-loaded in the first sentence. The following sentences each carry a distinct behavioral fact (history, irreversibility, alternative tool, deferred timing), though the ZenMode pacing sentence is somewhat long-winded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive batch mutation with no output schema, the description covers the essentials: scope (one campaign, up to 100), irreversibility, side-effect timing, and the safer alternative. Combined with annotations that flag destructiveness and idempotency, an agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so campaign_id, contact_ids, and idempotency_key are all documented in the schema itself. The description restates the 'up to 100 contacts' bound (matching maxItems) but adds no format or syntax detail beyond structured fields. Baseline 3 applies when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Remove up to 100 contacts from one campaign') and immediately grounds it in a familiar analog ('exactly like Remove in the dashboard'). It differentiates itself from the sibling set by naming set_contact_outreach_state as the alternative for temporary stops.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent: use this to permanently end outreach, use set_contact_outreach_state with pause to stop temporarily. The 'cannot be added back to the same campaign' note effectively flags the inverse of add_leads_to_campaign, so when-to-use and when-not are both covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial context beyond the annotations: no state change to the campaign, no LinkedIn-side action at call time, and a handoff token that only launch_campaign can redeem. The claim that it 'changes nothing' sits in mild tension with readOnlyHint=false, but the scope of 'nothing' is clearly campaign/LinkedIn state, not server bookkeeping, so this reads as nuance rather than contradiction. Token lifetime and any rate limits are left unspecified.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core fact (same preflight as launch_campaign, returns summary and token) and immediately dispels the side-effect assumption. The closing sentence on ZenMode's pacing engine is slightly tangential but supports the 'nothing happens now' message.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with full schema coverage and no output schema, the description covers what comes back (summary and confirm_token), the non-mutating nature, and where the token is consumed. Remaining gaps, such as behavior on a non-paused campaign or token expiry, are minor but real.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters are documented there (campaign_id source, idempotency_key semantics), so the schema carries the load. The description adds flow meaning by introducing the confirm_token the next call needs, but says nothing specific about campaign_id or idempotency_key usage. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (run preflight) on a specific resource (a paused campaign) and names the exact sibling it parallels (launch_campaign) and the one that performs the real action. An agent can distinguish this from launch_campaign and pause_campaign without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Makes the use case explicit: call this first for a paused campaign, then call launch_campaign with the returned confirm_token. It also preempts the most likely misuse by stating this call does not activate anything. It stops short of stating what to do when the campaign is not paused or when the token has gone stale.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by disclosing the shape of the result (id, campaign, status, outreach state) and the set of outreach state values, which no structured field provides since there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the search scope and followed by the return shape; almost every clause carries information. The searchable-field list slightly duplicates the query parameter description, which is the only waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only search tool with no output schema, the description supplies both the filter surface and the return fields, while annotations cover the safety profile. Nothing an agent needs to select and invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3 and the schema already documents limit, offset, query, status, campaign_id and include_removed. The description adds the enumeration of outreach states returned (active, paused, excluded, not_interested, removed), which is not present in any parameter description and clarifies what the status/removed filters ultimately surface.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Find contacts across your campaigns') and enumerates the searchable fields (name, company, job title, LinkedIn URL), so the agent knows exactly what this retrieval does. It does not explicitly name the sibling it contrasts with (get_contact for a single contact), so it falls short of full sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'optionally within one campaign or one status' implies when to apply the campaign_id/status filters, but there is no explicit when-to-use guidance, no exclusions, and no routing to alternatives such as get_contact or list_campaigns. Usage is inferable rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds substantial behavior beyond the annotations: server-side validation against validate_message rules, refusal with issues, empty-string clearing, full replacement of follow_ups, approval removal for approved campaigns on another account, no immediate LinkedIn action, and later paced execution by the campaign engine.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core action and then covers the important behavioral consequences in a compact paragraph. It is dense but most sentences earn their place by clarifying validation, replacement, approval, and timing behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive mutation with no output schema, the description is quite complete: it covers validation, side effects, approval impact, and execution timing. The main remaining gap is that it does not describe the success return value, though the annotations and schema carry much of the structured burden.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all parameters. The description still adds meaningful semantics by explaining that an empty follow-up string clears that step and that follow_ups replaces the whole list, which goes beyond the schema's field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: setting a campaign's connection note and up to three follow-ups. It also scopes the tool to campaigns that open with a connection note and distinguishes it from validate_message by explaining that server-side validation happens regardless.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a clear context—campaigns that open with a connection note—but does not explicitly say when to use this instead of siblings such as set_lead_messages or validate_message. Usage is implied by the campaign-level message semantics rather than stated as a routing rule.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: it discloses that nothing happens on LinkedIn at call time, that the campaign engine acts later within limits/hours/pacing, the exact refusal conditions (restricted, paused-for-week, cooling down, off) with reasons and lift times, and that stop-only actions are never refused. It also confirms idempotency_key makes retries a no-op, matching the idempotentHint annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the first sentence, followed by action semantics and then edge-case behavior. It is somewhat long for a three-parameter tool, but nearly every sentence carries behavioral information an agent needs, so little is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and mostly does so, describing refusals, reasons, and that the response indicates deferred processing. It stops just short of fully specifying the success/response shape, leaving a minor gap for a state-changing tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds real value by explaining the behavioral effect and reversibility of each action enum value (pause/exclude/not_interested) and the idempotency-key no-op semantics. The schema's own "What to do." action description is thin, so this compensation matters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states a specific verb and resource ("Change how ZenMode treats one contact") and then enumerates the actions with precise scope. It clearly differentiates contact-level state changes from campaign-level siblings like pause_campaign/resume_campaign by noting pause affects only this campaign while exclude affects every campaign.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Each action value is given its condition and undo path (pause→resume, exclude→unexclude, not_interested→dashboard), which tells the agent when each applies. However, it never explicitly compares this tool to sibling alternatives such as pause_campaign or remove_leads_from_campaign, so the routing is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only say destructive/idempotent/openWorld=false; the description adds substantial non-redundant behavior: validation rules (oversized note refused, not shortened; missing variable refused; unknown follow-up step refused), {{calendar_link}} substitution, and that AI stops writing for that contact once text is set. It also discloses that nothing happens on LinkedIn at call time and that the campaign engine applies the text later within daily/weekly limits, business hours and pacing — exactly the timing semantics an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single dense paragraph, front-loaded with the core action and followed by constraints in a sensible order (validation → AI behavior change → timing). No filler sentences, though the validation clause is a long run-on that packs three refusal rules into one sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, non-readonly mutation with no output schema, the description covers the critical unknowns: what gets replaced, what is preserved, what is refused, and when the effect materializes. It stops short of describing the returned result shape (e.g., what confirmation or validation errors come back), which is the only material gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all six parameters; the description nonetheless adds meaning beyond it — that follow_up_N must correspond to a step the campaign actually has, that variables are substituted with contact name/title/company/location, and that {{calendar_link}} becomes a tracked link. It does not clarify the interaction between the idempotency key and partial updates, which the schema covers only generically.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb+resource and scope: 'Set or replace the connection note and follow-ups ONE contact in a campaign will get, instead of the campaign's own.' This immediately distinguishes it from the campaign-level sibling set_campaign_messages (message text per campaign) without the agent needing to open either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clear usage context: use it to override the campaign's own text for a single contact, with the constraint that only steps not yet sent can be set and omitted steps are kept. It does not explicitly name set_campaign_messages or set_contact_outreach_state as alternatives, so routing to the correct sibling still requires inference from scope wording.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'changes nothing in the account.' Beyond the annotations it adds genuine interpretive context that the structured fields cannot convey: the server cannot see whether the app is installed, so 'not seen yet' also covers installed-but-never-signed-in, and the link handles both cases. It does not address idempotency (annotations say idempotentHint=false), which is a minor gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core outcome (state plus what to do next) is front-loaded in the first sentence, and the remaining sentences cover the state model and the 'not seen yet' caveat. It is slightly long but every clause carries information; nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description fully carries the return-value burden: it names the link, the per-OS command, and the latest version, and pre-empts the ambiguous 'not seen yet' case. For a no-required-param read-only tool, an agent has everything needed to call it and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single 'os' enum is documented as narrowing commands to that system, so the schema does the heavy lifting. The description mentions Mac/Windows commands but adds no syntax or behavior beyond the schema's own wording, matching the baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb phrase ('works out where the desktop app stands... and returns what to do next') and enumerates the concrete states it resolves (not seen yet, out of date, closed, open) plus the payload (link, command, version). It is clear on its own, but it never distinguishes itself from near-name siblings like get_desktop_app or get_setup_status, which an agent could easily confuse with this one.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the agent can infer this is the tool to call to determine the app's state and next action, and the 'campaigns only run while the app is open' line hints at why you'd call it. There is no explicit when-to-use/when-not statement and no sibling is named as the correct alternative for a related need (e.g. get_desktop_app), so the routing burden stays on the reader.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: despite readOnlyHint=false and idempotentHint=false, it explains that the call creates a checkout link and changes nothing else on the account, that a 30% first-month offer may be attached, and that get_setup_status will reflect the new plan afterward. That is exactly the side-effect and state-transition context the annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core behavior and is mostly dense with useful constraints, but the trailing remark about get_setup_status returning next_step.say is tangential to this tool and the plan/interval defaults duplicate the schema. Slightly longer than necessary, though no sentence is outright waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Strong coverage of preconditions, side effects, and sequence for a mutating setup tool with no output schema. The gap is return shape: it never says where the link appears (field name) or whether links expire or are reusable, which matters since there is no output schema to fall back on.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with enum descriptions for both parameters, which already state the practitioner/monthly defaults. The description repeats those defaults but adds no new semantics such as eligibility differences per plan or interval consequences beyond the trial. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb and resource: returns a Stripe checkout link for a free 14-day trial. It also scopes the audience (accounts with no plan, Practitioner and above) and names the related siblings (get_setup_status, get_desktop_app), so an agent can tell it apart from the rest of the setup family.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use and when-not-to-use: only accounts with no plan yet, only Practitioner and above, and Novice has no MCP or API. It even supplies the ordered setup sequence (get_setup_status → start_trial → get_desktop_app) so the agent knows where this call sits relative to alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Far exceeds what the annotations convey: annotations only flag destructive/idempotent/not-readOnly, while the description discloses the async execution model (nothing happens on LinkedIn at call time), the refusal reasons and reset timing, and the interaction with daily/weekly limits, business hours, and pacing. It also explains idempotency_key retry semantics in behavioral terms.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The one-line purpose is front-loaded and the rules that follow are dense but each sentence carries distinct behavioral information (clearing, validation, async timing, refusals, idempotency). It is longer than typical, but the length is justified by the tool's async and gated behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter mutation tool with no output schema and non-trivial gating logic, the description covers what is needed to call it correctly: partial update semantics, validation behavior, refusal conditions, and the fact that the response reports deferred work. Nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage the baseline is 3, but the description adds real meaning beyond the schema: 'Pass only the fields to change; null clears a field' defines partial-update and clear semantics, and it explains that industries are validated exactly against LinkedIn's list with unsearchable names reported rather than dropped.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a concrete verb+resource and scope: 'Change who a campaign finds,' then narrows it ('Only targeting can be changed here'), which cleanly separates it from siblings like set_campaign_messages, pause_campaign, and get_campaign_targeting. An agent can identify the operation without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives strong conditional guidance on when the call is accepted vs refused (account restricted, paused, cooling down, switched off) and clarifies that stop-outreach calls are never refused. It does not, however, point to alternatives such as get_campaign_targeting for reading current targeting, so it stops short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/destructive/idempotent, so 'Changes nothing, contacts nobody and uses no AI' is partly reinforcement, but it usefully rules out side effects like outreach that an agent might otherwise fear. The rule enumeration (banned phrases, per-kind length limits, follow-up format, placeholder handling) is genuine added context beyond the annotations, though the output shape is only sketched as 'each issue'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded in the first sentence and the trailing sentences clean up behavior and the placeholder caveat. It is slightly dense with parenthetical detail but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does the necessary work by saying it 'Returns each issue so it can be fixed,' and it covers side-effect concerns and per-kind rules. A brief note on whether the check is strict/blocking or advisory would make it fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds real meaning: 'kind' determines which limit applies (characters for the note, words for a follow-up), and it clarifies that template placeholders like {{first_name}} are permitted rather than flagged. That is interpretation guidance the schema alone does not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Check') and resource ('one connection note or follow-up you have written') and then enumerates exactly what is validated: banned phrases, length limits, follow-up format, nonexistent placeholders, and {{signal}}. This is concrete enough that an agent can distinguish it from any sibling tool without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Frames the usage clearly as a pre-save check ('against the same rules ZenMode enforces when it is saved'), which tells the agent when to reach for it. It does not name an alternative tool or state exclusions, so it stops short of the explicit when/when-not bar.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.