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

Beyond readOnlyHint/openWorldHint, the description discloses real behavioral facts: default and max timeout values, that timed_out:true is not a failure, and that calls are free (no credit debit). That credit-cost disclosure is genuinely valuable context not available in annotations. It stops short of describing the report payload shape or what happens on repeated polling.

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 dense, front-loaded sentences with no filler; the terminal-status conditions and cost note are stated up front. The parenthetical 'timed_out:true is success — call again or use check_report_status' is compressed to the point of mild ambiguity but earns its space.

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 two-parameter polling tool with no output schema, the definition covers timing, terminal states, cost, and the meaning of a timeout result. The main gap is the unresolved timeout-max conflict and the absence of return-payload detail, but the essentials for correct invocation are present.

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 50%: report_id is described in the schema, timeout_seconds is not, so the description's default/max information is needed. However, the stated max of 12 directly conflicts with the schema's maximum of 180, which can mislead an agent into an artificially low timeout. That inconsistency undercuts the added meaning.

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 names a specific verb (poll) and resource (an intelligence run) and states the terminal conditions (completed/failed/partial/timeout). It hints at the sibling by saying 'use check_report_status', but does not clearly define how the two differ, so an agent must infer the split.

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?

There is implied guidance: polling a run and the fallback 'call again or use check_report_status' after a timed_out result. What is missing is an explicit when-to-use-this-vs-check_report_status rule, e.g. 'use this when you want to block briefly; use check_report_status for a non-blocking single check'.

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