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

Annotations already declare readOnly, idempotent and non-destructive, so the bar is lower; the description still adds the meaningful detail that nothing is "created or sent" (no statements dispatched as a side effect). It also pre-describes the per-policy result shape and the failure message, which annotations cannot convey. The read-only restatement is slightly redundant but harmless reinforcement.

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?

Four short sentences, front-loaded with the core action, then results, then rationale, then cost comparison. No filler; only the trailing read-only sentence overlaps with the annotations, which is minor waste.

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 an output schema present, the return contract is covered, and the description still sketches the per-policy payload and error message. For a two-parameter read-only diagnosis tool, the only real gap is the undocumented id parameter.

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%: organisationId is documented in the schema, while id has no description. The phrase "against the contact" hints that id refers to a contact, indirectly compensating for the gap, but it never states this outright or clarifies that id differs from the invoice-oriented sibling's parameters.

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?

"Checks every policy in the organisation against the contact and its invoices" is a specific verb plus resource with explicit scope (all policies, current state). It also implicitly separates itself from check_invoice_policies by naming that sibling as the faster alternative.

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 a concrete use case ("Explains why a contact did or did not get a statement or other contact level action") and a comparative cost signal ("Slower than check_invoice_policies"), which steers an agent toward the cheaper sibling when contact-level explanation isn't needed. It stops short of an explicit "use this when / not when" rule, so not a 5.

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