diagnose_public_url

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

With no annotations, the description carries full burden. It thoroughly describes behaviors: single-probe from gateway-us-east-1, cache-warming side effect (probeMayHaveWarmedCache), error conditions (403/400), output fields (expected/observed SHA256, invalidation, hint), and actionable next-steps. This exceeds typical transparency.

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?

The description is concisely structured with front-loaded purpose and limitation, followed by usage guidance, output details, and edge cases. Every sentence adds distinct value without redundancy.

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?

Despite no output schema, the description enumerates all key output fields (expectedSha256, observedSha256, invalidation, hint, probeMayHaveWarmedCache) and explains error conditions. It fully compensates for missing structured documentation, making the tool self-contained.

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% with both parameters described. The description adds contextual meaning: url format expectations (full blob URL, custom domain rules) and project_id ownership. This provides more practical guidance than the bare schema.

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 the tool returns live CDN state for a public blob URL, specifying it is probed from a single gateway and not a global view. This distinguishes it from possibly similar tools like deploy_diagnose_url and wait_for_cdn_freshness.

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 explicitly says to use this when a deployed asset shows the wrong version or cache staleness is suspected. It also mentions limitations (not global view) and error conditions, but does not directly mention alternatives or when not to use.

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