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

Annotations only say it's a non-read-only, non-destructive, closed-world write. The description goes well past that: secrets are redacted before storage, the team replies by email and never through this tool, there's a 10-per-hour cap, and projectId requires view access. These are exactly the operational facts an agent cannot infer from annotations.

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?

Opens with the core purpose, then exclusions, then required payload content, then constraints (redaction, reply channel, rate limit). Every sentence carries a distinct operational fact; nothing repeats the schema or the 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 tool with an output schema and rich behavioral constraints, this covers what an agent needs: what counts as a valid report, what to include, what gets redacted, and how the response arrives. It even mentions the return shape ({ reportId, message }) despite the output schema existing, so nothing critical is missing.

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 baseline is 3; the description nonetheless adds meaning beyond the schema by saying to 'pass projectId when the problem is in a project, so the team can open it' and by requiring the tool name and exact error text in the description payload. It doesn't restate the 4,000-character bound, but the schema already carries that.

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: reporting a defect in Morpha itself to the Morpha team, with concrete qualifying examples (tool errors when it shouldn't, results contradicting docs, renders that don't match describe_video). No sibling tool does anything similar, so differentiation is implicit but 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?

Explicitly names when to use it and when not to: 'Not for your own mistakes (a wrong id, a bad argument the error already explained) and not for feature requests.' That exclusion set is exactly the confusion an agent would have here, and the usage conditions are enumerated rather than implied.

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