RingGuard — AI Receptionist for Trade Businesses

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

Annotations only declare a non-read-only, non-destructive, closed-world profile. The description adds two genuinely useful traits beyond that: a duplicate-phone warning tied to visible leads, and a mandatory two-step draft-then-confirm workflow. It still omits permission requirements and whether the draft is persisted or discarded.

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?

Three short sentences, front-loaded with the purpose and with no filler. The terse 'Two-step: draft, then confirm' fragment is efficient but slightly clipped.

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 nine-parameter mutation with no output schema and thin annotations, the description covers the workflow and duplicate handling but leaves the draft's return shape, required fields, and undo/rollback behavior unexplained. Adequate but with real gaps.

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 only 11% — essentially just the 'confirm' flag — so the description must carry the load for nine parameters. It gestures at the confirm semantics via 'draft, then confirm' but never explains business_name, phone format, email, notes, or the other fields, leaving most parameters 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 ('Add a new lead to your pipeline') and immediately scopes it to pipeline leads, which differentiates it from siblings like convert_trial_to_lead and claim_lead. It does not name an alternative tool explicitly, so it does not reach the sibling-differentiating bar of a 5.

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 draft/confirm flow and the duplicate-phone warning imply appropriate usage, but the description never states when to use this instead of convert_trial_to_lead or claim_lead, nor any prerequisites. Usage is inferable but not directed.

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 openWorldHint=false, so safety is covered. The description adds genuinely non-obvious behavior: without lead_id the result is scoped to calls *you* logged, not all calls, and the window is the last N days. It omits ordering and the limit/pagination 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 sentence that front-loads the primary mode and conditions the fallback mode. No filler, no restatement of the title, every clause carries 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 simple read tool with no output schema, the scoping semantics are covered, but limit, result ordering, and return shape are absent while all three parameters sit at 0% schema description coverage. Adequate but with visible gaps.

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 0%, so the description must carry parameter meaning. It conveys the role of lead_id and days ('last N days') but never mentions the limit parameter at all, and adds no format, range, or default detail beyond what the schema already encodes.

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 resource (logged calls) and two precise scopes: calls on a given lead, or the caller's own calls within a day window. This clearly separates it from write-side siblings like log_call, though it never names an alternative 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?

Gives the branch condition that selects each mode ('if no lead is given'), which is real routing guidance an agent can act on. It stops short of stating when not to use the tool or pointing to siblings such as lead_details or my_follow_ups.

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 declare a non-read-only, non-destructive, closed-world mutation. The description adds genuine context beyond that: the lead comes from a shared pool (so the action is visible to other users) and the operation is two-phase with an explicit draft step before commitment. It does not mention failure modes such as a lead already being claimed, or undo 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?

Two short sentences, zero filler, with the core action and its scope front-loaded before the workflow note. Nothing could be removed without losing 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 small mutation tool with no output schema, the description covers what the operation does and the draft/confirm protocol. It stops short of stating permission requirements, error behavior for already-claimed leads, or how this interacts with the sibling undo_last_change.

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 50%: confirm is documented in the schema, lead_id is not. The description adds one real constraint the schema lacks — the lead must be 'unclaimed' — but says nothing about the UUID identifier format or failure cases. Baseline 3 for partial coverage 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?

The description gives a specific verb and resource ('Take an unclaimed lead') plus the scope of the operation ('from the shared pool into your own pipeline'), which separates it from add_lead (creating new leads) and find_leads (searching). An agent can tell what this tool does 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?

The phrase 'Two-step: draft, then confirm' implies the required workflow and is reinforced by the schema's confirm description, but no alternative tool is named and no when-not-to-use condition is given. Usage is implied 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?

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), and the description adds genuinely new behavior: the operation is staged as draft-then-confirm, so the agent learns a mutation is not committed on first call. It stops short of describing what happens on confirm failure or whether a trial can be converted twice.

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, no filler, with the outcome stated before the two-step mechanics. Every clause carries information the agent needs.

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 mutation with no output schema, the description covers the core flow but omits what the draft actually contains, what the confirmed result looks like, and prerequisite/error conditions (e.g. invalid or already-converted trial_id). Adequate but with clear gaps.

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 50%: confirm is described in the schema, trial_id is only constrained by format/pattern. The description reinforces the confirm semantics ('draft, then confirm') but adds no format, resolution, or ID-sourcing detail beyond the schema. 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 ('Turn ... into') plus both the source (Shadow Trial signup) and destination (lead at shadow_trial stage), so the agent knows exactly what is produced. It does not explicitly contrast itself with the nearby siblings add_lead or new_trial_signups, which is the only thing keeping it from a 5.

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?

'Two-step: draft, then confirm' gives workflow context, and the confirm parameter clarifies the approval gate. However, it never says when to prefer this over add_lead (manual creation) or how it relates to new_trial_signups, so the alternative-selection guidance is implied 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?

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description earns extra credit by disclosing the data-visibility scope (own leads plus the unclaimed pool), which is genuine behavioral context not present in the annotations, though it says nothing about result volume, ordering, or pagination 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?

Two sentences, front-loaded with the core action and scope before the filter list. Every clause carries information; no filler or restated title text.

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 seven-parameter, zero-required search tool with no output schema, the description covers the action, the visibility scope, and the filterable fields adequately for correct invocation. The main omission is the 'limit' parameter and any note on what the result set contains, but the essentials 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?

With schema coverage at only 43%, the description carries weight by enumerating the filterable dimensions (name/phone text, status, industry, city, minimum lead score), which maps to five of seven parameters. However, it never mentions the 'limit' parameter and only alludes to 'scope' indirectly, so two parameters remain undocumented in both the schema and the prose.

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?

Names a specific verb (Search) and resource (leads) and adds a meaningful scope qualifier ('your own plus the unclaimed pool') that separates it from single-lead siblings like lead_details and from action siblings like claim_lead. It stops short of naming a sibling tool explicitly, so it is clear but not maximally differentiating.

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 visibility scope ('leads you can see') is implied as the condition for using it, but there is no explicit when-to-use/when-not guidance and no pointer to alternatives such as top_leads_to_call or lead_details for retrieving a single record. 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds that the response is comprehensive ('everything about one lead'), implying no filtering or pagination, but says nothing about permissions, missing-lead behavior, or result size.

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 lists the payload by category. No filler and no redundancy.

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 usefully enumerates the returned content categories, which is the main thing an agent needs. It omits any parameter guidance, which is the one remaining gap for a one-argument read 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 description coverage is 0% and the description never mentions the lead_id parameter beyond the phrase 'one lead'. It does not clarify that the argument is a UUID identifier or how to obtain one, leaving the sole required parameter largely undocumented.

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 resource and enumerates its returned contents (contact info, pitch angles, deal details, call history, notes), so an agent knows exactly what it fetches. It does not explicitly contrast with siblings like find_leads or call_history, but the 'one lead' scoping is clear.

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 by the purpose: fetch the full profile for a known lead. It never states when to prefer this over find_leads (discovery) or call_history (call-specific view), nor any prerequisite such as needing an existing lead_id.

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 openWorldHint=false, so safety and scope are covered structurally. The description adds real value beyond them by disclosing the pipeline cadence (runs every 4 hours) and roughly what is returned, but it says nothing about freshness semantics, staleness thresholds, or error/empty states.

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 dense sentence with the key noun phrase front-loaded and the returned facts placed up front rather than buried. The parenthetical pipeline diagram is compact and informative, though the sentence does pack three ideas together, reducing scannability slightly.

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 takes on the job of describing the return content, and it does so at a high level ('when it last delivered leads and how many'). For a zero-parameter, read-only diagnostic that is sufficient to call the tool correctly, though exact field names and response shape remain undocumented.

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 there is no parameter semantics for the description to clarify; the baseline of 4 applies. Nothing in the description misdescribes inputs, and it correctly presents itself as a no-argument status check.

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 names a specific resource (the automated lead-gen pipeline) and states exactly what it reports: last delivery time and lead count. It is clearly distinct from lead-oriented siblings like find_leads or add_lead, though it never explicitly contrasts itself with pipeline_report, which is the closest potential overlap.

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 by the content ('health of the pipeline'), with no statement of when to call it, when not to, or which sibling to prefer for adjacent questions such as pipeline_report or my_stats. An agent can infer a diagnostic use case but gets no 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 only declare readOnlyHint=false and destructiveHint=false. The description adds the important behavioral fact that some outcomes silently move the lead's stage (won, trial_started, appointment_booked, not_interested, do_not_call), which the agent cannot get from the annotations. It does not state permissions or reversibility.

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?

Three short sentences, front-loaded with the core action, then side effects, then the workflow. No filler or repetition.

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 six parameters, the description covers the essential mutation semantics and the draft/confirm workflow. The gaps are minor: no mention of notes/direction behavior and no indication of whether the stage change is reversible via undo_last_change.

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 only 33%, so the description must compensate. It explains the outcome side effects and implies the follow-up parameter, but notes and direction are never mentioned, and there is no syntax guidance beyond what the schema's follow_up_at description already supplies.

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?

Specific verb+resource: 'Record a call with one of your leads', and it goes further by naming the conditional side effect (stage changes for certain outcomes). It never names a sibling such as call_history or top_leads_to_call, so the agent must infer the distinction from the resource 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?

'Two-step: draft, then confirm' gives real procedural guidance for the confirm flag, but that is largely restated from the schema's confirm description. There is no guidance on when to use this tool instead of call_history or undo_last_change.

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 declare readOnlyHint=true and openWorldHint=false, so safety is already established. The description adds that no sign-in is needed, which is useful context, but doesn't describe the computation or output format. The 'ask the user' instruction is behavioral guidance but not deep transparency.

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?

Three sentences, front-loaded with the main purpose, then the sign-in note, then the user-input instruction. No wasted words, though the last sentence could be more tightly integrated.

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 estimation tool with no output schema and full parameter documentation, the description is nearly complete. It could mention what the output looks like or how the cost is calculated, but it covers the essentials.

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 fully documents all four parameters with defaults and constraints. The description reinforces the required inputs and the default-assumption nature, adding slight value beyond the schema.

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 (estimate) and resource (revenue lost to unanswered calls), and names the exact inputs (call volume, average job value). This distinguishes it clearly from siblings like ringguard_cost_estimate and my_stats.

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?

Implies usage ('Ask the user for their numbers rather than guessing them') but doesn't explicitly say when this tool should be used vs alternatives like ringguard_cost_estimate. No exclusions or prerequisites are 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description usefully adds what comes back (identity and a pipeline count), but says nothing about freshness, scope of the count, or what 'pipeline' includes. Adequate with the annotation assist, not rich.

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 tight sentence that front-loads the two things returned. No filler, though it is arguably terse enough to leave scope ambiguous.

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 return-value burden and does so briefly: signed-in user and pipeline count. That is close to sufficient for a trivial zero-arg read tool; only the meaning of 'pipeline count' is left undefined.

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 no parameters, so there is nothing for the description to disambiguate. Baseline 4 applies per the zero-parameter rule.

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 scope: the currently signed-in user plus a pipeline count. That is clearer than the sibling my_stats or team_leaderboard, though it never explicitly contrasts itself with those tools, so an agent must infer the difference.

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?

There is no guidance on when to call this versus my_stats, my_follow_ups, or pipeline_report, which all sound adjacent. The agent is left to infer that this is the identity-plus-summary entry point.

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 openWorldHint=false, so safety is covered. The description adds two genuinely useful behavioral facts not in the annotations: overdue items are included, and results are sorted soonest-first. It says nothing about the look-ahead window or result size, which would be the remaining behavioral 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?

A single tight sentence with the resource, the filter, and the sort order front-loaded. Every clause carries information; 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 simple read-only list tool with annotations covering safety, the description is nearly adequate. However, with no output schema and no explanation of days_ahead or the returned lead fields, an agent cannot tell how to control the window or what it will receive.

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 0% and the sole parameter days_ahead (default 7, range 0-90) is never mentioned in the description. 'Follow-up due' vaguely implies a time window, but the agent gets no hint that the horizon is tunable or what the default is, so the description fails to compensate for the coverage gap.

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 resource (your leads) with a precise filter (follow-up due, including overdue) and an ordering guarantee (soonest first). This distinguishes it from broad siblings like find_leads or top_leads_to_call, though it doesn't name those siblings 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?

No when-to-use or when-not-to-use guidance and no mention of alternatives such as top_leads_to_call or find_leads. The agent must infer the selection condition from the phrase 'follow-up due' alone.

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 openWorldHint=false, so the safety profile is known and the description doesn't need to restate it. It adds that the data is scoped to the caller ('Your') and names the aggregate categories, but says nothing about auth requirements, rate limits, or the shape of the response beyond a prose list. Moderate added value against annotation coverage.

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 leads with the resource and scope, then lists the returned aggregates with no filler. It is compact and readable, though the compressed colon-list is the only structuring device.

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 low-complexity, read-only, one-optional-parameter stats tool with annotations carrying the safety profile and no output schema, the description covers the essentials: what is aggregated, whose data, and the time window. Minor gaps (default value, response shape) are tolerable at this complexity.

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 0%, so the description must carry the parameter meaning, and 'over the last N days' does clarify that the single 'days' parameter is a lookback window rather than something else. However, it omits the default (7) and the 1-365 bounds, leaving part of the semantics to the schema.

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 names a specific resource (your call activity) and enumerates the returned aggregates (outcome totals, conversations, trials started, wins), so an agent can tell it apart from call_history or pipeline_report. It stops short of explicitly contrasting itself with the closest siblings (e.g. team_leaderboard, my_follow_ups), which keeps it at a 4 rather than a 5.

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?

There is no when-to-use statement, no prerequisites, and no mention of alternatives among the many sibling tools (pipeline_report, team_leaderboard, call_history). The personal scope implied by 'Your' is the only contextual cue, which is weak guidance at best.

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 declare readOnlyHint=true and openWorldHint=false, so the agent knows it's a safe, closed-world read operation. The description adds the filter condition (unconverted signups) but doesn't mention pagination, return format, or whether results are sorted. With annotations covering safety, this is adequate but not rich.

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 a single, efficient sentence that front-loads the key condition. It is appropriately sized for a simple query tool, though it could be slightly more structured by stating the action explicitly.

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 tool's simplicity (2 parameters, no output schema) and annotations covering safety, the description provides the core filter but omits parameter explanations and usage context. It is minimally complete but leaves gaps for an agent to infer how to use the parameters effectively.

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 0%, so the schema provides no descriptions for the 'days' and 'include_converted' parameters. The description doesn't explain these parameters at all. However, with only two parameters and a default behavior implied by the description ('haven't been converted'), the baseline of 3 is appropriate, but the description fails to compensate for the lack of schema documentation.

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 clearly defines the resource: businesses that signed up for the free Shadow Trial on ringguard.online and haven't been converted to a lead. This distinguishes it from siblings like find_leads or convert_trial_to_lead by focusing on unconverted trial signups. It doesn't explicitly state the action (e.g., 'retrieve' or 'list'), but the context implies a query.

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?

There is no explicit guidance on when to use this tool versus alternatives like find_leads or claim_lead. The description implies it's for fetching unconverted trial signups, but doesn't state when to choose it over other lead-finding tools or what prerequisites exist.

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 openWorldHint=false, so the safety profile is covered structurally. The description adds the useful behavioral detail that this is a read-only aggregated snapshot spanning several domains, but says nothing about freshness, cost, or whether the result is scoped to the calling user.

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 a colon introducing the payload contents. Every clause earns its place and there is no 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 carries the burden of describing the return contents, and the enumerated list largely does that. It stops short of specifying the shape or grouping of each section, but for a zero-parameter read-only report this 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 there is nothing for the description to disambiguate; baseline 4 applies. No parameter guidance is required or missing.

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 names a specific resource (pipeline snapshot) and enumerates its contents: leads by stage, won deals and MRR, follow-ups due, unclaimed pool, and open trial signups. That is far more concrete than a tautology, but it never distinguishes itself from adjacent reporting siblings such as my_stats or team_leaderboard.

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?

There is no statement of when to use this tool versus alternatives, nor any prerequisites or exclusions. The agent must infer from the word 'report' that this is the general overview, while siblings like my_follow_ups or new_trial_signups cover overlapping slices.

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 openWorldHint=false, so safety is covered. The description adds the useful auth context that no sign-in is required, which is a real value-add beyond annotations, though it says nothing about determinism or rate 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?

Two tight sentences, front-loaded with the purpose, with no filler. Every clause carries 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 simple two-parameter read-only estimator with no output schema, the description covers purpose, comparison basis, and auth. It could hint at what the estimate returns (cost breakdown vs. single figure), but the gap is minor.

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-3 assumption for avg_call_minutes and the overflow/after-hours meaning of calls_per_month. The description only loosely restates calls_per_month, adding nothing beyond the schema; 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 (estimate) and resource (RingGuard monthly cost) and names the comparison baseline (receptionist/answering service), which clearly differentiates it from the sibling missed_call_cost.

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 explicit when-to-use or alternative routing is given, though the comparison framing and 'No sign-in needed' imply the prospecting/evaluation context. Adequate but leaves the agent to infer when to call it over missed_call_cost.

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 this is a non-read-only, non-destructive, closed-world write, so the safety profile is covered. The description adds genuinely useful behavior beyond that: a 48-hour trial window, a human follow-up within one business day, the consent/privacy-policy gate, and that no sign-in is required.

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?

Four sentences, each carrying distinct information: purpose, downstream effect, precondition, and access requirement. The consent precondition is front-loaded after the purpose, and there is no filler. Slightly long but every clause earns its place.

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 form-submission mutation with no output schema, the description covers what an agent needs: the effect of the call, the post-call timeline, and the consent requirement. It does not address duplicate submissions or confirm whether a lead record is created, which is a minor remaining 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 only 22% across 9 parameters, so the description must carry more weight. It clarifies the most consequential parameter ('agreed_to_be_contacted' as a hard consent gate, reinforced by the privacy policy URL), but says nothing about the optional city, state, industry, or message fields. It partially compensates rather than fully closing the gap.

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 names a specific verb and resource ('Sign a business up for RingGuard's free 48-hour Shadow Trial') and specifies the trial duration, so the agent knows exactly what the tool creates. It does not, however, differentiate itself from the sibling 'add_lead', which an agent could easily confuse with a trial signup.

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?

It gives a clear, explicit precondition for use: only call after the person has provided details and explicitly agreed to be contacted and to the privacy policy. It also states the downstream effect (RingGuard follows up within one business day). It stops short of naming an alternative tool or an explicit when-not-to-use case.

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 openWorldHint=false, so safety is covered. The description adds the owner-only auth constraint, which is genuinely useful behavior beyond the annotations, but says nothing about ranking ties, result size, or how reps with zero activity are handled.

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 short sentences, zero filler, with the owner-only constraint front-loaded ahead of the effect. Every clause earns its place.

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-parameter tool with no output schema, the description covers auth scope, time window, unit of aggregation, and ranking criterion. Only the days default/bounds and any zero-activity handling are 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 coverage is 0%, so the description must carry the single parameter. 'Last N days' does convey the meaning of the days parameter, but omits the default (7) and the 1-365 bounds that the schema defines.

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 ('call activity per rep') with scope ('over the last N days') and ordering ('ranked by conversations'), which separates it from individual-level siblings like my_stats. It doesn't name a sibling explicitly, so it stops short of a 5.

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?

'Owner only' gives a real precondition for use, but there is no guidance on when to pick this over my_stats, pipeline_report, or call_history. Usage is implied by the resource scope 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?

Annotations already cover safety (readOnlyHint=true, openWorldHint=false), so the lower bar applies. The description adds real value beyond them: the ranking logic (lead score plus cost of the open receptionist job) and the fact that each result includes a suggested cold-call angle, which is non-obvious output content.

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 sentence that front-loads the resource and immediately qualifies it with ranking and inclusion criteria; no filler and nothing 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 does well to describe the ranking and the returned call angle. But it omits the two parameters and gives no routing guidance relative to its many siblings, leaving gaps an agent must guess at.

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 0% and neither 'limit' nor 'industry' is mentioned anywhere in the description. With two undocumented parameters, the description leaves the caller to infer that results can be capped or filtered by industry.

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?

Names a specific resource (leads to call) and defines its scope precisely: 'not yet won or lost, with a phone number, ranked by lead score.' That filtering criteria distinguishes it from siblings like find_leads or my_follow_ups, though no sibling is named 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?

'Right now' and 'best leads to call' imply a prospecting/cold-calling use case, but the description never states when to prefer this over find_leads, my_follow_ups, or lead_details, nor any prerequisites or 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=false, destructiveHint=false, and openWorldHint=false. The description adds real value on top: the two-step draft/confirm workflow and the fact that only the single most recent assistant-made change is targeted. It does not describe what happens if there is no change to undo, which is a minor omission.

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 short sentences with no waste. The core action and its scope are front-loaded, and the workflow note follows. Every clause earns its place.

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 one-optional-param mutation tool with no output schema and full annotation coverage, the description supplies the essential workflow and scope. It could be stronger by noting the outcome when no prior change exists, but nothing needed to 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 coverage is 100% and the single parameter already has a detailed description, so baseline is 3. The description's 'Two-step: draft, then confirm' reinforces the confirm flag's role in the workflow, adding light context beyond the schema.

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 (Reverse) and resource (the most recent change you made through Claude), then enumerates the exact change types covered (claim, new lead, status change, logged call, trial conversion). An agent can tell precisely what this does 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?

Clearly states the scope of applicability — it only reverses the most recent change made through this assistant, which prevents misuse for arbitrary/older changes. No alternatives exist among siblings, so no differentiation is needed; the only gap is the absence of explicit 'when not to use' 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 declare a non-destructive write, but the description adds genuinely valuable behavioral context the annotations cannot convey: the operation is staged, requiring a draft first and a confirmed second call. This tells the agent the mutation is gated on user approval, which is meaningful beyond readOnlyHint/destructiveHint.

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 short sentences, action first and the two-step constraint second. Nothing is wasted and the critical caveat is front-loaded.

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 3-parameter mutation with no output schema, the essentials are covered: what changes, which entity, and the confirm gate. A brief note on what a draft returns or whether changes are reversible would close the remaining 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 only 33% – only 'confirm' is documented, while 'lead_id' and 'status' carry no prose. The description maps 'status' to 'pipeline stage' and hints at the draft/confirm mechanics, partially compensating, but it adds no format or constraint detail for lead_id beyond the schema's uuid pattern.

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: 'Move one of your leads to a new pipeline stage.' An agent can distinguish it from add_lead, claim_lead, or convert_trial_to_lead by the 'move to a new stage' framing, though no sibling is named 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?

The 'Two-step: draft, then confirm' line gives a procedural cue, and the schema's confirm description reinforces it. However, there is no guidance on when this tool applies versus alternatives such as start_shadow_trial or convert_trial_to_lead, which also touch lead lifecycle state.

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 openWorldHint=false, so safety is covered. The description adds real context beyond that: no authentication/sign-in is required, and it scopes what content is returned (capabilities, pricing, comparisons, trial details). That auth disclosure is the kind of operational detail 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 dense sentence with the core subject front-loaded, followed by the content enumeration and the no-sign-in note. Every clause earns its place, though the long parenthetical list makes it slightly heavier than needed.

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?

There is no output schema and no parameters, so the description carries the burden of explaining what the agent gets back, and it does so by listing the topics covered. For a simple zero-arg info tool this is essentially complete; only the response format (prose vs structured) is unspecified.

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 is empty, so there is nothing for the description to disambiguate. Baseline 4 applies since no parameter semantics exist to document.

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 ('Explains') and resource ('RingGuard') and enumerates the exact content covered: capabilities, pricing, receptionist/answering-service comparison, and the free Shadow Trial. It is clearly the informational/overview tool among siblings like ringguard_cost_estimate and start_shadow_trial, though it never names those siblings 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?

'No sign-in needed' is a genuine usage condition and implies this is a safe first-touch orientation call. However, there is no explicit statement of when to choose this tool over ringguard_cost_estimate or start_shadow_trial, so the routing guidance is only implied.

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