AI Agents API Library

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

Annotations already declare readOnly, idempotent, non-destructive, non-open-world. The description goes well beyond them by disclosing data provenance ('Values carry the vendor page they were read from and a check date'), freshness metadata, and the key operational caveat that a docs-only server does not call the API. That is genuine extra context for a read tool.

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, but the remainder is one sprawling sentence with nested parentheticals that enumerates every returned field. Given there is no output schema the enumeration earns its place, yet the structure is hard to scan and the lists would read far better as bullets.

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 full burden of describing return values, and it does so comprehensively: top-level entry fields plus the signal blocks (uptime, mcp_repo, mcp_registry, product_reviews, sdk_downloads, stackoverflow, app_store, github_issues) with their metrics and fetch dates. An agent knows what it will get.

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 sole parameter ('id', with 'Service id from search_apis') is already fully documented in the schema. The description adds no syntax, format, or sourcing detail about the id, so the baseline of 3 applies.

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

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

Opens with a concrete verb+resource: 'Full entry for one service', which clearly contrasts with the sibling search_apis (list) and get_reviews (one signal). However, it never names a sibling or explicitly states the single-service scope as a differentiator, so an agent must infer the distinction.

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 / when-not-to-use guidance. The parenthetical about a repository needing installation versus a docs-only server is a behavioral caveat, not a routing rule, and no alternative tool is mentioned.

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 safety profile is covered. The description adds genuine value beyond that: reviewer names are excluded, reviews are third-party authored, and reviews do not indicate task fit — real behavioral caveats an agent needs.

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

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

Front-loads the core purpose and return fields, then moves to filters and caveats. Dense but each sentence carries information; only the about_api expansion mildly duplicates the enum.

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?

Covers the return shape despite having no output schema, and annotations handle the safety profile. The only loose end is a referenced `topics` field/behavior that appears in neither the schema nor an output schema, leaving minor ambiguity.

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 documents all 7 parameters with examples and enum values. The description restates filters (since, max_rating, about_api) and expands about_api to essentially the enum list, adding little 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+resource ("Public user reviews of one service") and enumerates the returned fields (rating, title, pros, cons, reviewer role, company size, date, link). It is clearly distinct from get_api and search_apis, though it does not explicitly name those siblings.

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 partial filter guidance ("Filter with since, max_rating (complaints) or about_api") and warns that "Reviews do not show whether the API fits the task," which is useful context. However, it never states when to prefer this tool over search_apis or get_api, nor any when-not condition.

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 the safety profile is fully covered. The description adds genuinely new behavioral context, namely that each category is returned with a service count, but says nothing about ordering, pagination, or scale 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 that carries the resource, the scope, and the one non-obvious output detail. Nothing is repeated and nothing is padded.

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 no-parameter, read-only catalog listing, the description plus annotations cover everything needed to invoke it, and the description compensates for the absent output schema by naming the returned fields. Minor gaps are ordering/pagination behavior when the catalog is large.

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

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

The tool takes zero parameters, so the schema and description have no parameter semantics to negotiate; the baseline for a no-param tool is 4. The description correctly implies the call is argument-free by describing a full unconditional listing.

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 categories in the catalog') plus the payload detail ('number of services in each'), so the agent knows exactly what it gets. It does not explicitly contrast itself with siblings like search_apis, but the resource is distinct enough that confusion is unlikely.

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

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

Usage is only implied: the agent can infer this is the tool to enumerate catalog categories, and there is no competing sibling for that resource. There is no explicit when-to-use statement, prerequisite, or routing guidance.

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

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

Annotations already declare a safe, idempotent read (readOnlyHint, idempotentHint, destructiveHint false, openWorldHint false) and the description honors them while adding material context: filter exclusion semantics ('services without reviews are excluded'), ranking weights and what ranking does NOT use (budget, region), the free_tier vs trial distinction, and the explicit caveat that exact matches are not proof the endpoint accepts the user's inputs.

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?

Purpose and eligibility caveat are front-loaded, then match semantics, then ranking, then each signal family in turn. Information density is high with little filler, but it is one very long block paragraph covering both filter semantics and output fields, which could be segmented for faster scanning.

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 the description compensates by naming the returned signals an agent must interpret (match, mcp_fit, ratings.usage, ratings.issues, reviews_summary, free_plan.kind) and warning that reviews rate the product rather than task fit. For a 15-parameter, zero-required search tool this is unusually complete.

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

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

Schema coverage is 93%, so the baseline is 3, but the description meaningfully extends it by explaining the match/mcp_fit output vocabulary and the ranking model behind sort=fit, plus how ratings.usage and ratings.issues are derived. Some parameter text (min_issue_health, sort enums, min_downloads) is largely restated from the schema, which keeps it from a 5.

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 ('Search 300+ catalog entries of third-party APIs and MCP servers'), specifies the search axis (operation or keywords) and the optional filter families. The catalog-search role is clearly distinct from sibling get_api (fetch one entry), get_reviews (review text) and list_categories (enumerate categories, which the description explicitly points to for category ids).

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 substantial usage guidance: it defines what the match labels mean, states that 'exact' is a search label not proof of input compatibility, explains what empty results mean, and tells the agent how to drive reviews/usage/issues signals via specific filters and sort values. It does not explicitly state when to prefer a sibling (e.g. 'use get_api once you have an id'), so it stops short of full when/when-not routing.

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