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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds that results are contacts rather than counts, but says nothing about pagination behavior, result ordering, or what happens for a campaign with no matching recipients.

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 with zero filler, front-loading the action and the filter dimension. Nothing is wasted or buried.

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, cursor-paginated list tool with no output schema and 75% schema coverage, the description plus schema covers what an agent needs to invoke it. Only minor gaps remain (paging behavior expectations, whether results are full contact objects).

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% and the status enum is fully enumerated in the schema, so parameters are largely self-documenting. The description's list of outcomes restates the enum rather than adding format or semantics beyond it, 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 gives a specific verb (List) and resource (contacts) scoped by campaign engagement outcome, which clearly separates it from siblings like list_contacts and campaign_report. It does not explicitly name an alternative sibling, but the outcome-filtering framing is distinctive enough for selection.

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 or when-not-to-use guidance and no mention of alternatives such as campaign_report (aggregate stats) or list_contacts (unfiltered). The only hint at usage is the enumerated statuses, which is implied context rather than stated 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 and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful return-shape detail — the exact metric set and per-link click breakdown — which matters since no output schema exists. It omits pagination/limits for per-link data, keeping it short of 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?

Two sentences, front-loaded with the core action and return contents, then a single usage cue. No filler or 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?

For a single-parameter read tool with annotations and no output schema, the description covers purpose, return contents, and a use case, which is nearly everything an agent needs. Minor gaps: no pagination behavior for per-link counts and no explicit boundary with sibling reporting tools.

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?

Only one parameter (campaignId) with 100% schema description coverage, including the helpful hint 'from list_campaigns'. The description adds no additional semantics beyond the schema, 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 gives a specific verb+resource ('Get a campaign's results') and enumerates the returned metrics (sent, opens, clicks, bounces, unsubscribes, complaints) plus per-link click counts, which is concrete and unambiguous. However, it never distinguishes itself from close siblings like get_campaign or campaign_recipients, so the agent must infer the split.

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 line 'Good for "how did last week's newsletter do?"' supplies a clear, recognizable usage context, which is stronger than vague implied usage. It stops short of naming alternatives or stating when NOT to use it (e.g., vs. get_campaign or campaign_recipients).

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=true, so the write/safety profile is covered. The description adds nothing beyond that: no note on side effects, uniqueness constraints, or what is returned, even though annotations would leave room for useful added context.

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 purpose is stated immediately. It is efficient, though its brevity borders on under-specification.

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 mutation tool with no output schema, zero parameter documentation, and only safety hints from annotations, the description leaves key details unstated (response contents, uniqueness, permissions). An agent can attempt the call but lacks context for correct handling.

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% for the single required 'name' parameter, so the schema only conveys the identifier and minLength. The description does not clarify what the name represents, whether it must be unique, or any format constraints, failing 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 verb and resource ('Create a new mailing list'), so an agent immediately knows the operation. It does not differentiate from siblings, though no sibling is a competing list-creation tool, so ambiguity is low.

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 guidance on when to use this versus list_lists/get_list, nor any prerequisites such as required permissions or whether the name must be unique. The agent must infer everything about invocation context.

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, readOnlyHint=false, and openWorldHint=true, so the irreversibility is partly covered. The description still adds value by stating the deletion is permanent and mandating user confirmation before invoking, which annotations cannot express. It stops short of describing idempotency or behavior when the contact is absent.

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, no filler, with the action and its permanence front-loaded before the safer alternative and the confirmation requirement. Every sentence carries a distinct instruction.

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 destructive tool with full annotation coverage and no output schema, the description supplies the essentials: permanence, a preferred alternative, and a confirmation gate. It omits only secondary details such as error behavior for unknown contacts or whether repeated calls are harmless.

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% for both parameters, so the schema already documents listId's source (list_lists) and contact's accepted formats (ID or email). The description adds no parameter-level detail beyond that, 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 ('Permanently delete a contact') plus the scope ('from a list'), which cleanly separates it from siblings like update_contact, upsert_contact, and get_contact. The adverb 'permanently' adds a meaningful qualifier rather than restating the name.

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 away from this tool when possible ('Prefer update_contact with status=unsubscribed') and adds a hard precondition ('Confirm with the user first'). Both when-not and the preferred alternative are named, leaving nothing to 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 and openWorldHint=true, so the safety profile is covered. The description adds value by enumerating the returned payload fields, which matters since there is no output schema, but it says nothing about behavior for a missing/invalid campaignId or about any content-size or truncation 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?

One short sentence that leads with the verb and resource and spends its remaining words on the most useful detail (the returned fields). Nothing is wasted and nothing is buried.

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-parameter read tool with annotations covering safety and no output schema, the description's field enumeration is the right compensating detail. It would be fully complete with a note on what happens when the campaignId is not found or how content is returned.

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 parameter already documents itself as the Campaign ID from list_campaigns. The description adds no parameter-level meaning beyond the schema, which is the baseline-3 case for a fully documented 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 and resource ("Get a campaign") and enumerates the returned fields (subject, sender, content, target lists), so the agent knows exactly what this returns. It implicitly contrasts with the plural sibling list_campaigns via the singular resource, but never names that distinction 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 description offers no when-to-use guidance, no prerequisites, and does not mention list_campaigns (the obvious way to obtain the required campaignId) or campaign_report as an alternative. Usage is only inferable from the tool name.

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=true, so safety and world-scope are covered. The description adds nothing behavioral beyond that: no not-found/error behavior, no note that a contact may exist in one list but not another, and no indication of the return shape.

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 identifies the action, the resource, and the accepted lookup keys with zero 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 two-parameter read-only lookup with full schema coverage and annotations covering the safety profile, the description covers the essentials. Only the not-found/ambiguous-match behavior is unaddressed, 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 coverage is 100%, so both parameters are fully documented in the schema, including that listId comes from list_lists. The description only restates the contact key formats (ID or email), adding no syntax or format detail 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 (look up) and resource (contact) plus the lookup keys (ID or email) and that it's scoped to a list. It is clear on its own, though it doesn't explicitly distinguish itself from the sibling list_contacts, which an agent could confuse with a single-contact lookup.

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 'look up a contact ... by ID or email' - retrieve one contact rather than enumerate - but no when-to-use, when-not-to-use, or alternative (e.g., list_contacts for enumeration) is named.

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=true, covering the safety profile. The description adds that the response includes custom fields and tags, which is useful return-context, but does not disclose any further behavior such as auth requirements or rate 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 no wasted words. The essential operation and its included data are stated immediately.

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 getter with one fully documented parameter and no output schema, the description adequately covers the operation and what content is returned. It could be slightly more complete by mentioning how the ID is obtained, but the schema already handles that.

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 listId parameter is fully documented in the schema (including its source from list_lists). The description adds no extra parameter 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 (Get) and resource (one list), and notes the included sub-resources (custom fields and tags). It distinguishes itself from list_lists by specifying 'one list', but does not explicitly name the sibling it is not.

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 guidance or alternatives are given. The description implies retrieving a single list by ID but does not state when this is preferable to list_lists or other list-related siblings.

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=true, so the safety profile is covered. The description adds genuine context by disclosing sort order and the fields returned per item, but says nothing about result volume, truncation, or that paging is cursor-based beyond what the schema 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 sentence that front-loads the resource and packs ordering plus returned fields into the remainder. Every clause earns its place with 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?

For a two-parameter, zero-required read-only list tool with no output schema, the description covers what the tool returns (campaigns with status and send dates) and in what order. Only pagination traversal and default page size are left unspecified, which the schema cursor field largely covers.

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 two parameters (limit, starting_after) are both self-documenting in the schema, so the baseline is 3. The description adds a small amount by implying a paged list ordered newest-first, which explains why a cursor parameter exists at all.

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 ('List email campaigns') plus useful qualifying detail: result ordering ('newest first') and payload contents ('status and send dates'). This clearly distinguishes it from the singular siblings get_campaign and campaign_report, though it never names them 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 only implied by the verb 'List' and the ordering note; there is no explicit statement of when to prefer this over get_campaign (single campaign), campaign_report (analytics), or campaign_recipients (per-recipient data). A standard enumeration tool needs little guidance, but nothing routes the agent among the four campaign-related siblings.

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=true, so safety is covered. The description adds genuinely useful behavior context — pagination with a 100-item cap and ISO 8601 date formats — but says nothing about auth requirements, rate limits, or how the cursor is used across calls.

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 with zero filler; the core operation and its filter dimensions are front-loaded, and pagination follows immediately. 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 9-parameter read tool with no output schema and low schema coverage, the description is adequate but not complete: it never indicates the shape of the response (contacts plus paging cursors), which matters because 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 only 44% across 9 parameters, so the description must compensate. It does add the ISO 8601 format for the four date-range params (the schema leaves them bare) and the 1-100 page-size bound, but it is silent on the required listId, the starting_after cursor, and the status enum values.

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 (List) and resource (contacts) scoped to a list, and enumerates the filter dimensions (tag, status, date ranges). It is easily distinguished from single-contact siblings like get_contact, 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?

Usage is implied by the phrasing 'List contacts in a list, filtered by...' but there is no explicit when-to-use guidance, no statement of when to prefer get_contact/upsert_contact, and no preconditions. An agent can infer the intent but gets no routing help.

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=true, so safety is covered. The description adds useful return context ('with their contact counts'), but says 'List all' without noting that results are paginated via limit/starting_after, which is a mild mismatch with real 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?

One short sentence, front-loaded with the verb and resource, and every clause (scope, contact counts) 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 simple read-only list tool with full schema coverage and no output schema, the description conveys scope and the headline return attribute. It omits any hint about pagination being required to retrieve everything, which is the only meaningful 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 100% and both parameters (limit, starting_after) are documented in the schema, so the description carries no parameter burden. It adds nothing about paging semantics beyond what the schema already states, which is the expected 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 and resource ('List all mailing lists') and adds the returned attribute ('with their contact counts'), which separates it from list_contacts and list_campaigns by resource. It stops short of explicitly naming which sibling to use for other listing needs, so it is clear but not fully differentiated.

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 prerequisite, and no reference to alternatives such as get_list (single list) or list_contacts. The agent must infer that this tool is the unfiltered enumeration of lists.

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?

With readOnlyHint=false and destructiveHint=false already declared, the description adds the crucial side effect that annotations omit: real emails go out, so user confirmation is required. It still doesn't say what happens on failure or whether the queue action is reversible, but the key risk is disclosed.

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, zero filler, with the core action stated first and the safety warning second. Every sentence 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 two-parameter, no-output-schema tool, the description covers what it does and the primary risk. Gaps are minor: no mention of the response, error behavior, or the contact/automation preconditions an agent would need before calling.

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%: 'contact' is documented (ID or email) while 'automationId' is bare. The description partially compensates by implying automationId must reference an automation configured with the 'Started via API' trigger, adding selection meaning 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 (queue) and resource (contact into an automation), and narrows it to automations using the 'Started via API' trigger. No sibling tool does anything similar, so an agent can select this without ambiguity.

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 supplies one important operational condition ('confirm with the user' because real emails are sent) but never says when this is appropriate versus other contact tools, nor any prerequisites such as the automation needing the right trigger and the contact existing.

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=true, so the safety profile is covered. The description adds that only existing contacts are touched and that status changes can effect an unsubscribe, but says nothing about permission requirements, whether omitted fields are cleared or preserved, or tag-removal side effects.

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 parenthetical example earns its place. It is efficient, though it is arguably too terse for a seven-parameter mutation tool.

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 43% parameter coverage across seven parameters, the description leaves real gaps: partial-update semantics, add/remove tag asymmetry, and how the required listId and contact pair interact are all unaddressed. The annotations cover safety, which lowers the bar, but the definition is still incomplete for a tool of 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 coverage is 43%, so the description must carry weight; it does map four of the seven parameters (email_address, fields, add_tags/remove_tags, status) and ties the status enum to a real scenario via 'unsubscribe'. It still does not distinguish add_tags from remove_tags, nor mention the required listId/contact pair beyond what the schema already documents.

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 (Update) and resource (contact) and enumerates the mutable surface: email, fields, tags, status. The word 'existing' implicitly separates it from the upsert_contact sibling, but the distinction is never made explicit, so an agent must infer it.

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 parenthetical '(for example, unsubscribe someone)' supplies one concrete use case, and 'existing contact' hints at the boundary with upsert_contact. However, there is no explicit statement of when to prefer this over upsert_contact or delete_contact, nor any prerequisite 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 readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so the safety profile is partly covered. The description adds useful behavior (custom fields keyed by tag, add/remove tags, status) but does not say whether an update overwrites or preserves omitted fields/tags, which matters for a non-destructive-flagged upsert.

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 core create-or-update behavior. It is efficient with no wasted clauses, though it tries to pack three capabilities into one line.

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 6-param mutation tool with no output schema, the description is adequate but thin: it omits the upsert-vs-update_contact routing decision and the overwrite semantics of updating an existing contact.

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%. The description explains that fields are set by tag, and mentions add/remove tags and status, adding meaning beyond the bare schema for those params. It does not address listId or email_address, though those are required and relatively self-evident.

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 and clearly captures the upsert semantics ('Create a contact, or update it if the email already exists in the list'). However, it never distinguishes this from the sibling update_contact, so an agent can't tell from the description alone which one applies.

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 or when-not-to-use guidance. With a sibling named update_contact that also mutates contacts, the choice between the two is left entirely to inference, which is a meaningful gap.

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