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

Annotations already declare this is a read-only, non-destructive, closed-world operation, so the safety profile is covered. Beyond that, the description adds genuinely useful behavior: grading is grounded only in the document's content, timeline scoring counts real dates/durations/quarters, and the answer shows the plan's own line per dimension plus missing elements and suggested sections. What it omits is the scoring scale or criteria behind each CRAFT dimension, which is the main thing an agent would want to interpret results.

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, front-loaded with the decision the tool supports and followed by concrete output behavior. It is dense but almost every clause carries information; the 'Timeline counts real dates...' clause is the only one that reads as a detail hung off the main thread.

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?

There is no output schema, so the description must explain the return value, and it does: a score per CRAFT dimension, the plan's own line per dimension, named missing elements, and suggested sections. What remains unexplained is the score range and what distinguishes a passing plan from a failing one, which an agent would need to report results meaningfully.

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 six parameters and the enums, making the baseline a 3. The description adds no parameter-specific meaning and, importantly, does not resolve the overlap between 'industry' and 'your_sector', which both carry near-identical enums and subtly different explanations.

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 gives a specific verb and resource: it takes 'the text of a GTM document or plan' and 'returns a score for each CRAFT dimension'. An agent can tell this is a document-scoring/readability tool rather than an analysis generator like competitive_intel or crisis_planner, but it never explicitly distinguishes itself from the closest sibling, pmf_scorecard.

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 implies usage ('decide whether a GTM plan is clear enough to run', 'paste the full text') and scopes the analysis to 'based only on what the plan contains'. However, there is no explicit when-to-use vs when-not guidance and no named alternative for adjacent needs such as scoring product-market fit.

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