find_similar

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

With no annotations provided, the description carries the full behavioral burden. It explicitly discloses that the tool is read-only, offline-only, reuses cached vectors without re-embedding, is a retrieval lead only, and returns an explanatory note rather than results when no model is installed.

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 compact, front-loaded with the critical 'Read-only' and core operation, and each sentence adds meaningful context: input, output, use case, and offline behavior. There is no filler or redundant restating of the tool name.

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?

The description covers purpose, use case, model behavior, offline constraints, and the no-model fallback. However, without an output schema, it does not describe the result shape or how limit and min_score affect returned results, leaving a notable but minor gap for a five-parameter tool.

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 only 40%, so the description needs to compensate. It does clarify the meaning of the anchor parameter and the model behavior, but it does not explain limit or min_score semantics, which remain under-documented in both the schema and the description.

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 operation: given a declaration anchor, return semantically similar declarations via the local embedding model. It clearly frames the tool as a 'what else looks like this' retrieval lead, which distinguishes it from sibling tools like concept_search and search.

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 gives concrete usage scenarios: finding sibling handlers, copy-paste variants, and peers of a function under review. It also notes the offline-only constraint and the fallback behavior when no model is installed, but it does not explicitly state when to prefer an alternative sibling tool.

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