diagnose_error

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real context the annotations don't: redaction guarantees (no password, session id, or document body echoed) and conditional behavior (Detective URL templates appear when req_id/chat_id are present).

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?

Short and front-loaded: the core purpose leads, then accepted/non-accepted inputs, then side-effect caveats. The terse 'Does not scrape Hub.' sentence is a stray fragment but the overall shape is efficient.

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?

Because an output schema exists, return values needn't be explained, and the redaction/URL-template notes are useful. But for a 16-parameter tool with zero schema coverage, leaving the majority of inputs undocumented is a real completeness gap.

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 0% across 16 parameters, so the description must compensate and largely doesn't. It names only about five inputs (symptom, req_id, hop name, HTTP status, result keys) and leaves chat_id, zeus_url, error_code, error_class, hop_bucket, session_id, turn_id, item_keys, node_keys, and body entirely unexplained in both schema and description.

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+resource: 'Map a symptom to failure_class + one generated-file change.' An agent knows the input (symptom text) and the output shape (a failure class plus a single file change). It isn't differentiated from the many siblings, but none of them are close enough to require that.

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 input-scoping rules ('Does not accept document bodies', 'Does not scrape Hub'), which imply usage boundaries, but never says when to reach for this tool versus doctor, readiness_check, or smoke_test_zeus. Usage is implied rather than directed.

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