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

Annotations only cover safety hints; the description adds genuinely new behavior: it refuses credentials and never contacts the target endpoint, and it operates on sanitized input. That is useful disclosure an agent cannot infer from readOnlyHint/openWorldHint alone. One unresolved tension: readOnlyHint=false suggests a non-read-only operation even though the description implies a pure offline analysis.

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?

A single front-loaded sentence with no filler; every clause (sanitized input, no credentials, no endpoint contact) earns its place.

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?

The output schema exists so return values need not be explained, which lowers the burden. Still, with 5 parameters at 20% schema coverage and no per-parameter guidance in the description, an agent gets only a partial picture of how to shape the call.

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 description coverage is only 20% (just endpoint), so the description must carry the load, and it largely does not. It hints that error_message should be sanitized and that no credentials belong in the call, but says nothing about what 'context', 'method', or 'endpoint' expect beyond the schema's own notes.

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 (diagnose) plus a tightly scoped resource (a sanitized HTTP 401 authentication failure), which naturally separates it from the sibling tools (json_schema, mcp, webhook_signature). It does not explicitly name the siblings or draw the boundary, but the object of diagnosis 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?

The description implies the usage context (you have a 401 auth failure to analyze) and adds two constraints — no credentials accepted, no contact with the target endpoint. However it never says when to prefer this tool over the sibling diagnose_* tools or what inputs make it applicable. Usage is implied rather than stated.

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