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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds cost ('Free') and a non-storage guarantee, but that guarantee is attached to 'Documents are validated in memory', which describes validation behavior rather than a rule-listing read — an irrelevant and potentially misleading behavioral claim.

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 description is front-loaded well with purpose and filters, but roughly half its length is a response-format dump (verdict, findings[], counts, data_confidence, sources[], disclaimer) that does not belong to a rule-listing tool and duplicates the existing output schema. That block crowds out more useful content such as jurisdiction semantics.

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?

An output schema exists, so the long return-value enumeration is redundant, while the genuinely unclear parts — what 'ae' vs 'ae-sb' jurisdiction selects and when to prefer this over validate_invoice — are never addressed. The copy-pasted validation response block makes the definition actively confusing for a read-only lookup tool.

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 33%: only 'contains' is documented in the schema. The description covers text filtering and severity filtering, and the severity enum (fatal | warning) is self-explanatory. However 'jurisdiction' (ae vs ae-sb, default ae) is explained nowhere in either the schema or the description, leaving a meaningful gap.

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 opening clause gives a specific verb and resource: rule ids, severities and texts from the installed PINT AE Schematron, with the filterable dimensions named. It is distinguishable from validate_invoice, but the trailing 'Response: result with verdict ... findings[] ...' block describes a validation output, which blurs what this tool actually returns.

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?

'Free' plus a worked filter example (contains 'TaxPointDate') imply exploratory lookup usage, but there is no explicit statement of when to call this instead of validate_invoice or readiness_report, and no exclusions. The agent must infer that this is the discovery/introspection counterpart to validation.

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