fow_traceability

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the bar is lower. The description still adds real value beyond them: bounded paged reads, no provider/model execution, and no authority mutation — useful scoping for an inspection tool. It does not note rate limits or auth specifics, but nothing is contradicted.

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?

Content is front-loaded and organized under Prerequisites/Effects labels, which helps scanning. The trailing 'Exact help' pointer to fow_capabilities is a useful affordance but adds boilerplate length, keeping it short of maximally tight.

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?

With rich annotations, full schema coverage and an output schema, the description does not need to explain return values and correctly avoids doing so. It covers prerequisites, effects and pagination adequately; only the relationship to sibling inspection tools remains unstated.

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 would be 3. The description goes slightly beyond the schema by conveying that milestone and evidence ID are alternative optional selectors and that audit detail is a distinct projection, which the raw schema does not spell out as relationships. It still doesn't clarify limit/offset semantics, so it is not a full 5.

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 states a specific verb ('Inspect') and a concrete resource set (requirements, milestone scope, recorded verification evidence and how they correspond). It is clearly traceability-oriented, but it never names a sibling tool it must be distinguished from, so the agent must infer the boundary with tools like fow_get_requirement or fow_audit_phase.

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?

It gives operating context ('Single operation; call directly without an operation argument') and prerequisites ('Select a project and optionally a milestone or exact evidence ID'), which tells the agent the entry conditions and the two read modes. It does not, however, state when to prefer this over the neighboring requirement/evidence tools, so the exclusions are only implicit.

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