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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior: the response is 'free of credits' (no cost), presentation is brief-first with a specific field ordering, and it warns against inferring confirmation or substituting zero for missing amounts, which materially shapes how an agent should use the result.

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 text is short with no filler, but it is fragmented and front-loads an output-presentation instruction ('Present brief first:') instead of a purpose statement. The four sentences are largely disjoint rules rather than a structured definition, making it terse but choppy.

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?

A precheck tool with a free-form plan object and an output schema is reasonably complex, and the output schema does excuse explaining return values. Still, the description omits any statement of what the check evaluates and gives zero coverage of the four inputs, so an agent cannot confidently construct a call from this definition alone.

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 0% across four parameters (symbol, as_of, plan, security_id), so the description must compensate and does not — none of these parameters is mentioned or explained. The only oblique hint is a reference to 'guidance.context', which gestures at the plan object's structure without defining it; an agent gets no guidance on formats such as how as_of is expressed or when security_id is needed.

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 implies a readiness/blocker-checking operation by promising 'grouped blockers, source dates, review items and next step', but it never states a clear verb+resource such as 'checks a research plan for blockers before running it'. The lead sentence describes what to present rather than what the tool does, so the agent must infer purpose from the name and the returned fields.

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?

'Reuse guidance.context when applying user-reviewed inputs' and 'Ready means calculable, not approved' imply a precheck-before-apply/start workflow, and 'Keep full guidance for follow-ups' hints at a follow-up turn. However, no sibling tool is named as an alternative and there is no explicit when-to-use versus when-not-to-use statement, leaving the routing to inference.

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