PulseGate

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered. The description adds value by disclosing the return shape (one row per platform plus an identifier count), which is not encoded in annotations or an output schema.

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

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

Two sentences, no filler: the first describes the output, the second states the purpose. The retrieval-relevant use case is front-loaded and nothing is repeated from the title or annotations.

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 zero-parameter vocabulary tool with no output schema, the description fully covers what an agent needs: what is listed, what accompanies each entry (counts), and why it matters for lookup_project.

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

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

The tool takes zero parameters, so the baseline is 4. The description still adds downstream semantics by tying the result to the 'platform argument of lookup_project', which is the only parameter meaning an agent needs to infer.

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 every platform PulseGate records identifiers on') and adds the returned dimension ('with how many identifiers it holds for each'). It also names its relationship to the sibling lookup_project, so an agent can distinguish it without opening either schema.

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

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

Gives an explicit use case: 'Use it to learn the vocabulary the platform argument of lookup_project accepts.' That clearly routes the agent here before calling lookup_project, though it does not state any exclusions or cases where this tool should be skipped.

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 read-only, idempotent, closed-world, non-destructive semantics, so the bar is lower. The description adds real context beyond them: results are evidence records with provenance and verification status, and it explicitly disclaims that this implies liveness, maintenance, or working software — a useful guard against misuse as a health check.

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 what is returned, then the scope disclaimer, then how to invoke. No filler; each sentence carries distinct 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?

With no output schema, the description helpfully characterizes the returned fields (identifiers, provenance, verification). It leaves unaddressed what happens with conflicting slug/value inputs, error behavior for unknown slugs, or result volume limits.

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 each of slug, value, and platform is already documented. The description adds the relational semantics the schema omits: these are alternative lookup paths ('by slug, or by an identifier you already have'), which matters given zero required parameters and no schema-level either/or constraint.

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: return the external identifiers PulseGate holds for one project, plus provenance and verification status per identifier. Scoping to 'one project' implicitly distinguishes it from search_catalog, but no sibling is named, so differentiation is left to inference.

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

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

Gives clear invocation context: 'Look up by slug, or by an identifier you already have,' which covers both entry paths an agent is likely to have. It does not state when to prefer a sibling (e.g. list_identifier_platforms or search_catalog) or when not to use it.

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 safety (readOnly, idempotent, non-destructive), so the description is free to disclose operation-specific behavior, which it does well: a hard cap of ten candidates, parity with native HTML/HTTP search, the unknown-vs-false semantics, and explicit non-goals (no complete profile, publisher fetch, bulk export, or functionality guarantee).

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, no filler, and the core capability (find software) is front-loaded, followed by return shape and then boundaries. Slightly dense but 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 read-only search tool with no output schema, the description gives enough for correct invocation: result cap, parity with HTTP search, unknown semantics, and explicit scope limits. The lack of explicit sibling routing is the main 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 100%, so the schema already documents all nine parameters including limits, page depth cap, license/pricing disclaimers, and the require syntax. The description adds little parameter-specific detail beyond the unknown-is-not-false semantics, so 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 ('Find software') and enumerates the search axes: by name, task, or recorded filters. This distinguishes it from siblings that list identifiers or look up projects, though it does not name 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 implied through the search axes and the closing exclusion list (no complete profile, publisher fetch, or bulk export), but there are no explicit when-to-use vs. when-to-use-alternative-VS-sibling statements. Siblings like list_identifier_platforms are never referenced as alternatives.

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