Search @imqueue documentation

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description still adds substantial behavioral context: the corpus spans both prose docs and generated API references, each result names its package and carries a URL, and queries may be plain questions or exact symbol names. It also discloses the package-ambiguity behavior and the search-then-read workflow, which no annotation could convey.

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 longer than average (~170 words), but every sentence earns its place: scope, result shape, query modes, purpose, and the list_packages routing caveat. Core function is front-loaded before the caveats, and there is no redundancy with the schema 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?

With 100% schema coverage, safety annotations, and an output schema present, the description covers everything an agent needs to invoke this tool correctly: what to search, how to phrase queries, which sibling to use instead in ambiguous package cases, and where results lead next. Nothing material 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%, so the baseline is 3, but the description adds meaning beyond the schema: it explains the query parameter's dual mode (plain question vs exact symbol names, with concrete examples like 'RedisQueue.send'), and clarifies the intended use of `package` (search within the package you settled on after list_packages). The `limit` parameter is already fully documented in the schema itself.

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 precise verb ('Search'), names the exact corpus ('official @imqueue docs... and every exported symbol of every @imqueue package'), and defines the output ('most relevant pages with their URLs'). It also distinguishes itself from siblings by explicitly noting that get_doc reads the pages it returns, so an agent can tell them apart immediately.

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 states when to use the tool ('Answers how do I do X in @imqueue' and confirms a signature before code is written) and when not to: for ambiguous queries like 'tracing' or 'database', it directs the agent to 'call list_packages for the choosing rule rather than taking whichever package ranks first' and then pass `package` here. The division of labor with get_doc is also made explicit.

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