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

Annotations already declare the safe read profile (readOnly, idempotent, non-destructive, not open-world), so the bar is lower; the description still adds real behavior beyond them — cap of 5 results, 3 by default, id/version/score fields, and that only a confident top match carries the input contract.

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 tight sentences: what it searches, what comes back, and what to do on a miss. Return details are front-loaded and nothing is padding.

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?

An output schema exists, so return values need not be spelled out, yet the description still sketches the shape. Combined with annotations covering the safety profile, an agent has everything needed to call it correctly and interpret a miss.

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%, so the description must carry the load and largely does: it conveys the query is a free-form English task, that limit tops out at 5 with a default of 3, and that include_contract governs whether the first match's input contract is returned. Upper bound and the 256-char limit of query are left to the schema.

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 the ComputeFirst catalog'), the input form (an English task), and the result cardinality. An agent can distinguish it from list_saved_tools or describe without opening any 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 clear context (natural-language task) and an explicit fallback for the no-match case: 'request_tool can ask for one.' It does not contrast with siblings like list_saved_tools, which catalog saved tools, so the routing guidance is clear but not exhaustive.

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