GTMMCPs GTM Research

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and a closed-world scope, so the safety profile is covered. The description contributes only the 2-5 ID window (already in schema) and an ambiguous claim about 'preserving unknown detailed coverage and individual sources' that does not clearly tell the agent how results are merged or what happens with unknown IDs.

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 preamble; the source-of-IDs constraint appears early. The 'preserving unknown detailed coverage' fragment is dense and hard to parse, costing some clarity for its brevity.

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-only tool with rich annotations this is close to sufficient, but with no output schema the description should indicate what the comparison returns (per-tool fields, sources, gaps) rather than alluding to it vaguely. The dependencies and error behavior on bad IDs remain unaddressed.

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

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

Schema description coverage is 0%, so the description must carry the load — and it does add meaning beyond the bare 'array of strings': the values must be exact catalog IDs obtained from search_gtm_tools, and the cardinality is two to five. It stops short of saying whether order matters or whether duplicates are rejected.

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 ('Compare ... catalog IDs') and scopes it to two to five IDs drawn from search_gtm_tools, which separates it from the sibling search tool. The trailing clause about 'preserving unknown detailed coverage and individual sources' is opaque and blurs rather than sharpens the purpose.

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 'exact catalog IDs from search_gtm_tools' implies the prerequisite that IDs must be discovered via the sibling search tool first, which is useful. However, there is no explicit when-to-use/when-not guidance and no statement of what to do if an ID is invalid or duplicated.

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

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

Annotations already declare readOnly/idempotent/non-destructive, so the description adds real value by disclosing coverage limits (not all companies are researched) and the two distinct failure/redirect outcomes. It stops short of describing the shape or size of the returned guide.

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 primary action, then the coverage caveat, then edge-case routing. No filler or restatement of the name.

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 should hint at the return; "sourced guide" is only loosely defined. However, for a single-parameter read tool it covers the failure modes an agent actually needs to handle.

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% and the single parameter is an undescribed string, but the description compensates by specifying that it accepts either a company slug or a catalog ID and by explaining suite-ID behavior. Format details (slug syntax, ID shape) remain unstated.

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 ("Retrieve the sourced guide") and names the two accepted identifier types (company slug or catalog ID). It is clearly distinguishable from the GTM-oriented siblings, though that differentiation is implicit rather than stated.

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

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

Gives explicit conditional guidance: only selected companies have detailed research, suite IDs redirect to choose_product with separate guide IDs, and unknown IDs yield not_researched. An agent knows what each input class will produce before calling.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds that only reviewed/curated updates are returned and that monitoring coverage is explicit, which is genuine behavioral context, but "monitoring coverage is explicit" is too terse to be actionable and the company_id/slug mismatch adds ambiguity.

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?

Short and front-loaded with the core action, which is good. However, the second sentence is compressed jargon that spends words without conveying a usable rule, so brevity here comes at the cost of clarity rather than from efficiency.

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?

A two-parameter read tool with no output schema and zero schema descriptions needs the description to explain what an update record contains and how results are ordered/bounded. It leaves both unstated, so an agent cannot predict the payload or pagination behavior.

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 only alludes to the company filter (and calls it a "slug" while the schema calls it company_id), and says nothing about limit, its default of 10, or the maximum of 20.

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?

"Read reviewed updates" gives a verb and resource, and "optionally for a company slug" scopes it, but what constitutes an "update" stays abstract. The second sentence drifts into content taxonomy (research additions vs vendor announcements) rather than sharpening the tool's purpose against siblings like search_gtm_tools or research_gtm_question.

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 word "optionally" implies the company filter is elective, but there is no statement of when to call this instead of search_gtm_tools, research_gtm_question, or get_company_guide. No exclusions, no prerequisites, no trigger conditions are given.

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

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

The description adds substantial behavior beyond the readOnly/non-destructive annotations: it lists the returned artifact, plan, provenance, missing questions, and non-sending preview, and explicitly rules out connecting to customer systems, reading records, running SQL, scheduling, writing, or sending. This is unusually transparent for a planning tool with no output schema.

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

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

The purpose is front-loaded in the first sentence, followed by return behavior, unsupported-case behavior, schema contract, and safety boundaries. Every sentence carries distinct operational value 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?

Given the complex nested input schema, absence of an output schema, and existing annotations, the description is complete enough for correct invocation. It explains return contents, unsupported-scope behavior, schema contract adherence, and the non-sending boundary.

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

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

Schema description coverage is 100%, so the nested request contract is already documented in the schema. The description adds only that the request follows request.schema.json and must be complete, without explaining individual field semantics beyond what the schema provides.

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 ("Build a design") and resource scope ("for intent expansion-account-review") and clarifies that it operates from a complete structured request. It is clearly distinguishable from the research/search/compare/update siblings, though it does not explicitly name those alternatives.

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 clearly states the supported intent and what happens for unsupported intents/adapters, giving useful when/when-not context. It does not explicitly route the agent to sibling tools for adjacent tasks, so it falls short of full alternatives 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 cover readOnly/idempotent/non-destructive/closed-world, so the bar is lower. The description adds real value beyond them: the return shape (citations, scope labels, limitations), the caveat that limitations may not apply to every answer, and the choose_product follow-up flow before making capability claims.

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?

Six tight sentences, front-loaded with purpose and return shape before parameter guidance and the choose_product note. Every sentence carries distinct information with no 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, the description proactively explains the return contents and the caveat around limitations, and it flags the choose_product decision point. For a read-only research tool with one required param, this is complete enough for correct invocation.

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 explains company_id scoping and both evidence_type enum values plus the omission case; only 'limit' and 'question' are left implicit, which is acceptable given 'question' is self-evident and limit is a bounded integer.

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

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

The description uses a specific verb ('Retrieve evidence') and states the resource ('plain-English tool question') plus what is returned (citations, scope labels, limitations, source links). It is clearly distinguishable from search/compare/list siblings by its evidence-retrieval framing, though it never explicitly names an alternative.

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 concrete when-to guidance: restrict company_id for a single vendor, choose evidence_type=vendor_documentation vs editorial_guidance, omit for mixed evidence and biographies. It doesn't name sibling tools or say when to prefer them, so it stops short of full alternative routing.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to add scope and output context instead. It does so well by naming the returned fields (catalog IDs, dates, source links, MCP status) and explicitly disclaiming verification — a real boundary an agent needs. Pagination and ranking behavior remain unstated.

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 clauses, zero filler: purpose first, then return contents and the key limitation. Every element earns its place and the caveat is front-loaded where the agent will read it.

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 steps in to enumerate return fields, and the explicit suitability disclaimer sets correct expectations for a read-only catalog search. Minor gaps remain around result volume, filtering behavior, and query syntax, but nothing essential to invoking it is missing.

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

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

Schema description coverage is 0% across three parameters, so the description bears the burden. It clarifies the `query` parameter (name or task) and partially gestures at `mcp_status` via 'recorded MCP status', but says nothing about `limit`, its 1–20 range, defaults, or what the enum values official/community/none-found/unknown/n-a mean.

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 ('Find candidate GTM tools by name or task') and signals a discovery/candidate scope, which usefully distinguishes it from compare_gtm_tools and research_gtm_question without naming them. Clear enough to act on, though a direct sibling reference would push it to 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 'by name or task' phrasing implies keyword/lookup usage, and 'does not verify suitability' implicitly tells the agent this is a first-pass discovery step, not an evaluation step. However, no alternative tool is named and no when-not-to-use condition is stated, so the agent must infer the handoff to compare_gtm_tools or research_gtm_question.

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