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

Annotations declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, and the description explains the non-obvious reason: the call queues a hosted asynchronous job rather than returning data directly. That resolves the apparent tension between a read-style 'inspect' and non-readOnlyHint, and 'redacted' signals sanitized content. It does not mention job lifetime, polling expectations, or permission requirements.

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?

Two sentences, no filler; the async-job consequence and the get_job follow-up are front-loaded right after the purpose statement.

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?

For an async, no-output-schema tool the description supplies the two things an agent most needs: what is inspected and that the result arrives via get_job. Missing only secondary details such as return shape and any auth/permission caveats beyond workspaceToken in the schema.

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 67%; requestId and workspaceToken carry their own descriptions (UUID reuse rules, secret handling), so the schema does the heavy lifting. The description adds only the implied meaning of projectId via 'workspace project graph' and no format or 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?

States a specific verb (inspect) and resource (redacted workspace project graph, capabilities, current revision), which is concrete and not a restatement of the name. It does not, however, distinguish itself from close siblings like get_workspace, get_runtime_status or list_projects, so an agent must guess which inspection tool to pick.

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 clear operational context: the call queues a hosted job and the result must be fetched with get_job — an explicit next-step alternative. It stops short of stating when to use this over get_workspace/list_projects or any exclusions, so it is strong but not complete routing guidance.

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