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

Annotations only declare readOnlyHint=false and destructiveHint=false, so the description carries most of the burden and does well: it discloses the project-level title uniqueness constraint, the workflow-stage gating rule, and that an id is returned. It omits failure behavior on duplicate titles, but the coverage is above average.

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?

Compact and front-loaded: creation, then title semantics, then workflow gating, then return value. Slightly dense/run-on in the third and fourth clauses, but no filler sentences.

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 a create tool with no output schema, the description covers the key facts an agent needs: uniqueness of titles, when writes are allowed during a run, and what is returned. Missing only error/duplicate-handling detail, which is minor.

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 description coverage is 100%, so the schema already documents all four parameters including requestId idempotency. The description only mildly extends this by saying titles are free-form and content is supplied 'when known' (i.e. optional), which is the baseline level of added meaning.

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 and resource ('Create an instruction document on a project') and clarifies the free-form title space, which distinguishes it from the many create_* siblings. It also points to update_instruction as the follow-up path, giving partial sibling differentiation.

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?

Adds a real usage constraint: instruction changes during an active workflow run are accepted only in its self-improvement stage. It also implies the create-then-update flow by noting the returned id feeds update_instruction. It does not, however, state exclusions against archive/delete siblings.

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