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

Annotations already mark this as a non-destructive write, but the description goes further: it discloses the global side effect (updating shared reliability scores for everyone), that the call is free and keyless, and a privacy contract (never send inputs, outputs, or prompts). It stops short of saying what happens to duplicate or malformed reports, so not quite a 5.

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?

Trigger condition is front-loaded in a labeled clause, then payload, then effect, then the caveat about auto-reporting. Four sentences, each carrying distinct information, no filler.

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?

Five simple flat parameters, full schema coverage, no output schema required, and the description still covers the trigger, the payload, the side effect, and the privacy boundary. An agent has everything needed to call it correctly and knows when not to.

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 every parameter including the enumerated error classes is already documented in structured fields. The description only restates the send list and flags errorClass as failure-only, adding marginal meaning beyond the schema — baseline 3 applies.

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?

Names a concrete verb (report) and resource (outcome of an external MCP tool call Glimind routed/checked) plus the effect: Glimind updates live reliability scores. That clearly separates it from read-only siblings like check_tool_reliability, list_breakages, and audit_server.

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?

Opens with an explicit WHEN TO CALL trigger — after a routed/checked call succeeds or fails — and adds a real exclusion: the SDK's execute() already reports automatically, so agents shouldn't double-report there. Alternatives and the condition for skipping are both stated.

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