diagnose

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

Discloses that full-projection app diagnose masks sensitive keys by default and reveals only when reveal=true. Also notes server action triggers non-blocking side-effect (D-10). Annotations only have openWorldHint=true, so the description adds valuable behavioral context.

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?

Three sentences with no waste. Front-loaded with main purpose, then security note, then side-effect. Each sentence 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?

Given the complexity (three action branches, many params), the description covers key behavioral aspects: masking, reveal option, side-effect. Output schema exists, so return values not needed. Complete and sufficient.

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. Description adds meaningful context about the reveal parameter (security warning) and implicitly covers trigger_validate via side-effect note. Justifies a score above baseline.

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 clearly states it synthesizes diagnose views for applications and servers, or runs a global fleet scan. It distinguishes three actions (app, server, scan) via the oneOf schema, differentiating it from sibling tools like database, project, etc.

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?

Provides guidance on when to use reveal=true (plaintext only when needed) and warns not to persist secrets. Mentions server action triggers non-blocking validation. However, does not explicitly exclude using sibling tools or state when not to use this tool.

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