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

Beyond annotations (which only mark readOnlyHint=false, idempotentHint=false, destructiveHint=false), the description adds a key safety guarantee: 'AST-only (your code is never executed)'. It also details the scope of checks. This meaningfully supplements the annotations, though it does not describe the return format or any side effects (e.g., does it write logs?).

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 a single, well-structured sentence that front-loads the primary action and timing, then lists the specific validation categories in a compact list. Every word contributes value; there is no fluff or repetition.

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 validation tool with no output schema, the description covers the main usage, safety, and scope. It does not state what the response looks like (e.g., a report of errors), which could be helpful, but the absence is not critical since the purpose is clear and the tool's behavior is predictable. Given the complexity (4 params, nested objects), it is reasonably complete.

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% – every parameter is already documented in the input schema. The description adds no parameter-level detail beyond what the schema provides, so the baseline of 3 applies. It does hint at the namespace check tying to project_uuid, but that is not a substantial addition.

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 verb (validate), the resource (locally-authored bundle), and the timing (BEFORE publishing). It enumerates the specific checks (manifest, syntax, import-safety, config exports, schema validity, namespace) which differentiates it from siblings like build_deploy or schema_validate.

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 positions the tool as a pre-publish validation step ('BEFORE publishing'), giving clear context on when to use it. It does not explicitly name alternatives or exclusions, but the purpose is specific enough that an agent can infer when it is appropriate.

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