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

Annotations already declare readOnlyHint/idempotent/openWorld, and the description goes further: it names the exact output file (vdd/impact-report.generated.md), guarantees hand-authored vdd/impact-report.md is never overwritten, and discloses the delegation-envelope fallback when artifactFiles is omitted on the hosted endpoint. That is unusually rich behavioral detail.

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-loaded with the core action and check list, then prerequisites, then parameter relationships. Dense but every clause carries information; only minor trimming is possible.

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?

An output schema exists, so return values need not be explained. The description still covers ordering, side effects, the hosted-vs-local distinction, and file outputs, leaving nothing an agent needs to call it correctly.

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 adds genuine cross-parameter semantics: feature narrows the check to one spec, and artifactFiles maps artifact path to content and is omitted when resolving against a local projectRoot. These relationships are not obvious from the per-parameter schema alone.

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 (Validate) plus resource (the full VDD chain) and enumerates exactly what it checks: traceability matrix, drift, orphan, uncovered vision goals, impact metrics, and 28 S&T assumption checks. It also names the sibling it is not (vdd_inspect) and the file it produces, so an agent can distinguish it from all other vdd_* tools.

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?

Explicitly says when to run it ('after implementation is complete') and names the concrete alternative for a sub-use case ('for the traceability matrix or per-feature spec metrics use vdd_inspect'). It adds environment-specific guidance (hosted/stateless vs local projectRoot).

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