usageReferences

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 covered. The description adds valuable behavioral context: the response is a 'flat list that is really a tree' and can be 'hundreds of rows and over a hundred thousand characters, past the response cap.' This warns the agent about a critical behavioral trait (response size) that annotations don't convey. It doesn't describe the exact return format, but the warning about size and structure is significant.

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 and front-loaded. The first sentence states the core function, the second warns about the response size, and the third routes to alternatives. Every sentence earns its place, and the critical warning about response cap is placed before the routing advice. No wasted words.

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 read-only tool with no output schema, the description covers the key operational aspects: what it does, how to invoke it (with/without position), the response size risk, and alternatives. The only gap is the lack of explicit return format details, but the warning about the tree-like structure and size is more important for an agent deciding whether to call it. The description is complete enough for an agent to make a correct call decision.

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 the description must compensate. It explains the semantics of the position parameters ('at a cursor position' implies line/column) and the optionality of position ('when no position is given' implies url alone works). However, it doesn't explicitly define what 'url' refers to (the object URL) or the exact format of line/column. The description adds some meaning beyond the bare schema, but not exhaustive.

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's function: 'Where-used for the symbol at a cursor position, or for the whole object when no position is given.' It specifies the resource (symbol/object) and the operation (where-used analysis), and distinguishes it from siblings like whereUsedMethod and impactOf. The verb 'where-used' is specific and the scope is well-defined.

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 explicitly tells the agent when to use this tool vs alternatives: 'Prefer impactOf, which asks this and rolls it up; use whereUsedMethod for one method by name.' This is a clear routing instruction that names the alternatives and the conditions for choosing them. It also warns about the large response size, which is a practical usage consideration.

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