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

The readOnlyHint annotation already establishes that this is a non-mutating operation, and the description adds meaningful behavioral detail beyond that: results are 'ranked selectors' and bodies are not returned. This is exactly the kind of extra context that helps an agent understand what to expect. There is no contradiction with the annotation.

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 two-sentence description is tightly written and front-loads the core purpose before adding the important exclusion. Every sentence contributes necessary information without filler. It loses a point for relying on jargon ('selectors') that is not defined and for omitting parameter guidance that could have been included in a compact list.

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?

Given five parameters, no output schema, and four sibling tools, this description is too sparse to fully support correct invocation. It conveys the basic search behavior but leaves parameter semantics, result format details, and sibling routing unexplained. An agent would likely need to open schemas or guess.

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?

With 0% schema description coverage, the description carries the full burden for parameter understanding, but it only hints that 'query' can be a prose phrase or an unknown identifier. The limit, intent, project, and version parameters are completely unexplained, leaving the agent to guess their roles. This is a significant gap for a 5-parameter tool.

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 clearly states the tool returns 'ranked selectors' for a 'prose query or unknown identifier,' which communicates the core search behavior and result form. The title adds the resource scope ('code and docs'), and the explicit 'Does not return bodies' helps distinguish it from a fetch operation. It could be stronger with a clearer verb like 'search' and explicit sibling differentiation.

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?

The phrase 'for a prose query or unknown identifier' gives useful context for when this tool is appropriate, and 'Does not return bodies' implicitly warns against using it when full content is needed. However, it never explicitly names sibling tools like web3_fetch, web3_grep, or web3_lookup or states when to prefer them. The guidance is implied rather than explicit.

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