llmref

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

Annotations already establish readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral context: fuzzy ranked matching, pagination, and source_root disambiguation when multiple slugs match, though it does not mention rate limits or auth requirements.

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 front-loaded with purpose and usage priority, then concisely covers query behavior, pagination, and disambiguation. Every sentence contributes without waste.

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 notes that each entry includes source_root and explains disambiguation. For a simple three-parameter discovery tool, this is largely complete, though it does not describe the full result shape.

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 defines skip, limit, and query. The description mostly restates the schema for query pagination and does not add significant syntax or semantic detail beyond the structured fields.

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—'List indexed documentation projects (version-pinned doc snapshots)'—and frames it as a discovery step before reading docs. It clearly distinguishes this from answering from memory or a latest-only source.

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 explicitly says 'Call this FIRST to discover the exact slug before reading any library's docs' and prefers itself over memory/latest-only sources. It does not explicitly compare against sibling tools like resolve_docs or search_docs, which would make the routing guidance complete.

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 that the output is a set of valid version strings usable as inputs elsewhere, but says nothing about result size, ordering, or behavior for an unknown project slug. Useful workflow context, but little behavioral depth beyond annotations.

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. The purpose is front-loaded and the downstream-call guidance follows immediately, so an agent can act on the first clause alone.

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 no output schema, the description covers purpose, downstream usage, and the nature of the return value (valid version strings). Nothing an agent needs in order to call it correctly or interpret the result 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 `project` parameter is documented in-schema with examples, so the schema carries the semantics. The description reinforces where the version value should come from (lockfile/package.json) but adds no detail about the project parameter itself. 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 ("List available snapshot versions for a project") and implicitly distinguishes itself from siblings by positioning itself upstream of resolve_docs and search_docs. An agent knows exactly what this returns (version strings) 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?

Explicit sequencing guidance — "Call this before resolve_docs or search_docs" — plus a concrete selection rule: match the version the user actually depends on from their lockfile/package.json rather than guessing. Both when-to-call and how-to-choose are spelled out, with the alternatives 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?

Beyond the annotations, the description discloses that this sends only the listed fields to a discovery queue, does not fetch or index, is best-effort, and should not be retried or announced. It also provides explicit privacy constraints about never sending prompts, code, private URLs, credentials, or user 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?

The description is front-loaded with the core purpose and then layers on operational rules. It is dense but each sentence carries actionable guidance; the only minor cost is that the single paragraph packs several distinct constraints together.

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 fire-and-forget reporting tool with no output schema, the description covers the essential behavior: what is sent, what is not done in this call, how to proceed afterward, failure handling, privacy limits, and skip conditions. An agent has enough information to invoke it correctly without expecting a synchronous result.

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 parameter meanings are already documented. The description reinforces that the version is the 'exact version sought' and that docs/llms.txt URLs should be observed public URLs, but it mostly repeats the schema rather than adding new syntax or format guidance.

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: 'report of public documentation missing from llmref.' It also clarifies the submission target ('discovery queue') and that no fetching or indexing happens in this call, distinguishing it from the lookup-oriented 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?

It explains when to report (missing public documentation), what to include (exact version and observed docs/llms.txt URLs), and when not to call ('Skip if reporting is disallowed or would require interrupting the user for permission'). It also tells the agent to continue with other sources rather than wait for ingestion or retry failures.

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 annotations already declare a read-only, open-world operation, and the description adds useful behavior beyond that: how to save `resolved_version` and `revision_id`, how to use `pinned_artifacts`, and how to interpret `version_provenance` labels. It does not describe pagination or error behavior, but for a resolution tool the main behavioral caveats are well covered.

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, and the remaining sentences contain actionable guidance rather than filler. It is dense with field names and caveats, but the density earns its place in a compact tool definition.

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, so the description carries the return-value burden, and it does so by naming `resolved_version`, `revision_id`, artifact URLs, `pinned_artifacts`, and `version_provenance`. For a two-parameter resolution tool, this is complete enough for an agent to call and interpret results correctly.

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 in the schema. The description still adds meaningful semantics for `version` by accepting `latest` and by directing discovery through `list_versions`, which goes beyond what the schema states.

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: resolving a project version or `latest` to documentation and artifact URLs. It clearly distinguishes this from siblings by referring to `list_versions` for discovery and `search_docs` for later use, so an agent can identify the tool 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?

It explicitly says to discover valid version strings with `list_versions` first, and it routes later exact-text lookups to `pinned_artifacts` and `search_docs` via `revision_id`. It also handles the important edge case of versions without a `revision_id`, telling the agent to continue with existing artifact URLs.

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 and openWorldHint, yet the description still contributes real behavioral context: the prerequisite feature flag, the graceful-degradation path, and that results come back relevance-ranked and bounded by token_budget. It stops short of covering edge cases like zero-hit results or how ranking/truncation interacts when the budget is exhausted, so it is strong but not exhaustive.

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, each doing distinct work: what it does, what it returns and how it is bounded, then the prerequisite and fallback. The core capability is front-loaded and no sentence is redundant with the title or schema.

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 correctly supplies the return shape (relevance-ranked chunks capped by token_budget) and the operational prerequisite, which is the information an agent could not get from structured fields. A small gap remains around the snapshot parameter's relationship to resolve_docs, which is only implied by 'version-pinned'.

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 baseline is 3, but the description adds interpretation the schema cannot: token_budget is framed as the cap on returned content and the output as ranked chunks, telling the agent how query and budget interact in practice. It does not further explain snapshot or top_k 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?

States a specific verb and resource ('Semantic search across a project's version-pinned documentation') plus the scope constraint (version-pinned) that separates it from generic doc reading. The final clause explicitly contrasts it with reading the whole llms.txt and names the sibling resolve_docs as the fallback, so an agent can route between them 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 a positive selection rule ('fastest way to pull just the passage you need for an exact version instead of reading the whole llms.txt') and a negative one ('Requires the server to have semantic search enabled; if it isn't, fall back to resolve_docs + reading llms.txt'). Both the when and the when-not, with the alternative named, are present.

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