findDefinition

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds the behavioral requirement that the source must be read first to count the position, which is not derivable from annotations. It also indicates the response contains the object and position of the declaration. This adds useful context beyond the annotations, though it does not cover potential error conditions or rate limits, which are not expected for a read-only tool.

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 two sentences with no fluff. It front-loads the purpose, then states inputs and prerequisite, and finally points to alternatives. Every sentence earns its place, and the structure is easy to scan. This is an ideal length for a tool description.

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 tool that finds a definition based on cursor position, the description explains the input requirements and the need to read the source first. It also mentions the output (object and position) and provides alternative tools. It does not elaborate on error cases or edge cases, but given the annotations cover read-only behavior and there is no output schema, the description is sufficient for an agent to invoke it correctly. The only minor gap is not detailing how line and column are specified, but that is implied by the context.

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 0%, so the description carries the full burden for parameter meaning. It explains that 'source URL with a line and column' are needed, which maps to url, line, startCol, and endCol. It also ties the source parameter to the need to read the source first. However, it does not mention mainProgram or implementation, which are likely optional but could have usage notes. Given the low coverage, the description adds significant meaning but not exhaustive documentation.

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 finds where a symbol under a cursor is defined, using the familiar metaphor 'the F3 of ADT'. It distinguishes itself from usageReferences and impactOf by naming them as alternatives for the reverse direction. This is specific and unambiguous, leaving no doubt about the tool's core function.

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?

It explicitly states the prerequisites: the source must be read first to count the position, and it takes a source URL with line and column. It also explicitly directs the user to usageReferences or impactOf for the opposite direction, providing clear guidance on when not to use this tool. This is exemplary usage guidance.

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