find_orphans

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

With no annotations, the description must carry the full behavioral burden, and it does disclose the key semantics: no inbound calls plus exclusion of HTTP entrypoints. The word 'candidates' usefully signals a heuristic rather than a guarantee. However, it omits the major behavioral caveats for dead-code detection (dynamic dispatch, reflection, cross-language or framework-invoked code) and says nothing about read-only safety or result ordering.

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?

One sentence, front-loaded with the payoff ('Dead-code candidates'), qualified immediately by the two defining conditions. No filler. Terseness works against it only in that the sentence is doing definitional rather than operational work.

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?

For a zero-required-param query with no output schema and no annotations, the description answers 'what does this return' conceptually but not concretely: no indication of return shape (symbol objects? file paths?), ordering, or whether the list is truncated at 'limit'. Adequate to call it, not adequate to interpret the result confidently.

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?

The single optional parameter 'limit' has 0% schema description coverage and the description never mentions it, so its meaning (max candidates returned? default 100?) is undocumented in every field the agent can see. Low stakes for a trivial integer, but the description adds no meaning beyond the raw schema type.

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?

Names the resource precisely: functions/methods with no callers that are not HTTP entrypoints, and frames the output as 'dead-code candidates'. An agent can tell this apart from find_references/find_callers because the defining condition (zero inbound edges) is stated. It stops short of a 5 because the verb is implicit and no sibling is named as an alternative.

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?

There is no when-to-use or when-not-to-use guidance relative to the many sibling graph tools (find_callers, find_references, impact_analysis). The HTTP-entrypoint exclusion is a scoping definition, not usage advice. Nothing warns that results are heuristics that should be verified with find_references before deletion.

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