exact_references

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

The description adds real behavioral context beyond the read-only annotations: Python results are heuristic, imported SCIP index freshness is unverified, and callers should inspect scope, ambiguity, and warnings. These accuracy caveats are exactly what an agent needs to interpret results; it stops short of describing failure modes or fallback behavior.

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?

Four efficient sentences with the core purpose front-loaded and no repetition. The phrasing is somewhat telegraphic ('Check scope, ambiguity and warnings'), which costs a little clarity but wastes no space.

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 six parameters and no output schema, the description does a good job covering accuracy expectations, result labeling, per-file totals, and warnings. It is nearly complete for calling the tool correctly, missing only explicit sibling routing and return-shape detail.

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 83%, so parameter documentation is already handled by the schema, which is the correct baseline of 3. The description adds only indirect meaning ('per-file call totals before limits' touches on the limit parameter) and no syntax or format details beyond structured fields.

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 opening sentence states a specific verb and resource: 'Find who calls or references a symbol.' The clause about TS/JS compiler bindings excluding same-named unrelated symbols implicitly distinguishes it from text-search siblings like grep/search, though none are named explicitly.

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?

Usage guidance is implied rather than explicit: 'Check scope, ambiguity and warnings' and the mention of Python being heuristic hint at when to trust results, but the description never states when to choose this over grep or search, nor any preconditions. Most disambiguation guidance lives in the schema, not the description.

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