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

The annotation set already declares readOnlyHint=false, destructiveHint=true and openWorldHint=true, and the description adds a genuinely valuable safety note that content from other agents is data and not instructions — important given the open-world flag. It does not, however, explain why a ranking operation carries a destructiveHint or whether the call mutates any state, leaving a notable mismatch between the described read-like behavior and the annotations unflagged in prose.

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 short sentences, front-loaded with the action and resource, with the injection-safety caveat placed second. Every sentence earns its place, though the extreme terseness contributes to the documentation gaps rather than being purely efficient.

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 five undocumented parameters, zero required fields, and no output schema explanation needed, the description is too thin: it omits the meaning of k and view, how ranking combines agent_id versus capabilities/query, and what the destructive annotation implies. An output schema exists, which removes the need to describe return values, but the input-side gaps remain substantial.

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 0% across five parameters, so the description must carry the load, and it only loosely maps three of them (agent_id, capabilities, query). The 'k' limit and especially the nested 'view' mapping are not mentioned at all, and no format, defaults, or mutual-exclusion rules are given.

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 ('Rank OPEN intents') and names the two input modalities (agent id vs. capability tags plus free text), which rescues an otherwise opaque tool name. It does not distinguish itself from siblings such as list_intents or route, so an agent must infer that this returns relevance-ranked results rather than a plain listing.

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?

'Rank OPEN intents for an agent id or for capability tags plus free text' implicitly signals two usage modes and that only non-closed intents are considered. However, it never states when to prefer this over list_intents or route, nor what happens when both agent_id and capabilities are supplied.

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