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

Annotations declare a non-read-only, non-destructive, idempotent operation; the description adds real value on top by imposing a per-conversation dedupe rule, a privacy constraint ('Do not include personal data about the user'), and the fact that the message must be self-contained for a reader without the conversation. It does not say what happens to a submitted report or who consumes it, but the output schema covers the response side.

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?

Four short sentences, front-loaded with the core action, then exclusions, rate limit, privacy, and the sibling redirect. No sentence is redundant with the name or title.

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 write-side reporting tool with six params and an existing output schema, the description covers the trigger conditions, the dedupe budget, the privacy rule, and the alternative route. An agent has everything needed to decide and to call it correctly without guessing.

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?

With 67% schema coverage the baseline is 3, and the description lifts it by mapping its trigger examples onto the category enum values (missing_capability, wrong_result, unclear_tool) and by scoping 'a missing bond' away from identifiers toward request_bond. The tool_error and 'other' categories remain unglossed, so it stops short of fully compensating.

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 gives a specific verb and target ('Report a gap in BondTerminal') and enumerates the triggering conditions: missing tool/field, wrong result, unclear description. It also names the sibling to use for a different case (bondterminal_request_bond), so the boundary is unambiguous.

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?

Explicit when-to-use is paired with explicit when-not-to-use ('searches you can fix by retrying or by using bondterminal_search_bonds'), a rate constraint ('at most once per distinct problem per conversation'), and a routing rule for missing bonds. This is the full when/when-not/alternative triad.

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