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

Annotations already declare readOnly/idempotent/non-destructive, and the description layers on non-annotation context: ~5-minute recheck freshness, a 404 unknown_provider error contract, and pricing (free within daily quota, then $0.003 via x402). It also enumerates the verdict domain, so the agent knows what it is receiving.

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?

Front-loads the purpose, then usage, then exclusions, then return shape and mechanics. Dense but every clause carries distinct information — no restatement of the title or name.

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?

There is no output schema, so the description carries the return contract itself and does so fully (summary, verdict enum, recommended_action, incidents, affected_components, checked_at, freshness). Combined with the error case, freshness window, alias, and pricing, an agent has everything needed to call and interpret the result.

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 the baseline is 3, but the description still adds meaning: the id must come from list_providers (not a display name), the sample invocation {"provider":"openai"}, and the failure mode for an unknown id. Useful reinforcement without syntax detail beyond the 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?

Opens with a specific verb+resource: check whether one named API provider is up, degraded, or down. It explicitly demarcates scope ('one ... provider' out of ~40) and names what it is not for, routing away from check_model_deprecation, list_recent_api_changes, and get_digest.

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?

Gives explicit when-to-use ('before calling that provider, or right after 5xx/429/timeouts'), the decision it supports ('choose retry, wait, or a fallback'), and explicit when-not-to-use with the three sibling alternatives named. Nothing is left to inference.

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