reef_where_used

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

Annotations already provide readOnlyHint and idempotentHint. The description adds behavioral context: it does not run grep, coverage explains limits, and returns fallback tool args. This adds value 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?

The description is a single dense sentence that front-loads purpose. It is efficient but could be split for readability. Every part adds value, but it is slightly verbose.

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 the output schema exists, the description need not detail return values. It covers coverage limits, fallback behavior, and the two-stage process. However, it lacks detail on what the answer structure looks like, and parameter semantics are weak.

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% so parameters are undocumented in schema. The description only implicitly mentions query and targetKind via 'symbol, component, route, file, or pattern', but provides no explanation of projectId, projectRef, freshnessPolicy, or limit. This is insufficient for correct parameter usage.

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 answers where a symbol, component, route, file, or pattern is defined and used, with a two-stage process from maintained state then indexed references. It explicitly says it does not run grep, distinguishing it from raw text search tools.

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 description implies usage for structural queries and mentions fallback behavior when maintained state has no answer. It explicitly states what it does not do (grep), but does not explicitly name alternative tools like live_text_search or cross_search.

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