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

Beyond the annotations (readOnlyHint=true, destructiveHint=false), the description explicitly confirms the read-only nature ('changes nothing'), specifies the external dependency (no API key), sets a time expectation (up to a minute), and explains the asynchronous result retrieval via check_id. This gives an agent a clear operational model without contradicting any annotation.

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 well-structured with the purpose front-loaded and supporting details following logically. It is a multi-clause sentence, but each part adds distinct value (scope, outputs, non-destructive behavior, auth prerequisites, timing). No superfluous content; only minor verbosity from the long list of outputs.

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 two parameters, no output schema, and moderate operation complexity, the description is complete. It tells the agent what the tool returns (services, missing items, fixes, env vars, cost across four providers), how to handle long-running checks, and the inputs needed. An agent can call this tool correctly with no missing behavioral or output expectations.

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?

With 100% schema description coverage, both parameters are already documented. The description adds valuable context by explaining that repo can be a path or URL and links check_id to the polling workflow ('if it's still running, call again...'). This goes slightly beyond the schema by clarifying how the parameters interact in practice.

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 opens with a clear verb ('Checks'), a specific resource ('public GitHub, GitLab or Bitbucket repository'), and a concrete goal ('will deploy'). It enumerates the exact outputs (services, missing items, env vars, cost across providers) and establishes a non-destructive scope ('Reads the code and changes nothing'), making its intent unambiguous and distinct from sibling tools like plan_deploy or redeploy.

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 offers solid contextual guidance: it states the tool applies to public repositories, requires no API key, and explains the polling pattern ('if it's still running, call again with the check_id it returned'). However, it does not explicitly state when to prefer this over alternatives (e.g., plan_deploy) or when not to use it, leaving some room for inference.

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