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

Beyond annotations (readOnlyHint=false, destructiveHint=false), it discloses that reports are stored privately under the caller's account and client, that no reply arrives in this conversation, that user consent is required for unsolicited reports, and that secrets/PII must be excluded. These are material behavioral traits an agent cannot infer from the schema or 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?

Four tight sentences, front-loaded with the usage triggers, then consent, privacy, and exclusions. Nothing is wasted, though the opening sentence could be sharper about the core action.

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 8 parameters, no output schema, and safety annotations already present, this covers most of what an agent needs: triggers, exclusions, consent, privacy, and content restrictions. The remaining gap is detailed guidance on the technical parameters (request_id, subject_id, subject_type), which the description leaves entirely to the schema.

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 50%, and the description only indirectly touches two fields ('Summarize' for summary, 'never include secrets' for details). It provides no guidance on 'tool', 'issue', 'subject_id', 'subject_type', or 'request_id', leaving half the parameters to the schema alone. Baseline 3 for moderate coverage with partial compensation.

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 makes clear this is a feedback-reporting tool for OpenApps failures, and explicitly scopes it away from other servers or the client app. It never states the action as a crisp verb+resource ('sends a report to OpenApps') up front, relying on implication, but the purpose is unambiguous in context.

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?

It gives explicit triggers (errors, wrong data, missing capability, confusion), an explicit exclusion (other servers, client app, task completion), and a consent rule ('Ask the user before sending a report they did not ask for'). This is exactly the when/when-not/alternatives guidance an agent needs.

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