describe_tool

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

Annotations already declare read-only/idempotent/non-destructive, yet the description adds genuinely new behavior: the catalog is loaded once at startup, repeats are cheap, there is no rate limit, and results stay stable until restart. It also documents the error path for unknown names (an error listing up to five closest names) and the rename/retirement resolution rules.

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?

Purpose and routing guidance are front-loaded, and the second paragraph covers input edge cases before the return shape. It is dense but nearly every clause carries information; the sentence about the catalog being loaded once is slightly buried but not wasted.

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?

There is no output schema, so the description enumerates the return fields ({ success, name, domain, description, inputSchema, annotations?, retired_name? }) itself. Combined with the error behavior and caching notes, an agent has everything needed to call it and interpret the result.

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 100%, so the schema already documents `name`, but the description adds real meaning beyond it: the name must come from find_tools, surrounding spaces are ignored, a current tool's name always wins, and old or retired names resolve with `retired_name` reporting the mapping. That resolution logic is not expressible in the schema.

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?

States a specific verb and resource: returns one tool's description, input schema and annotations. It explicitly positions itself between find_tools (discovery) and call_tool (invocation), so an agent can distinguish it from every sibling without opening a schema.

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?

Gives an explicit trigger ('use it before call_tool when find_tools' parameter line does not say how to fill an argument, such as its format or allowed values') and an explicit exclusion ('a tool already in your list has its schema there'). The alternative it replaces is named directly.

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