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 layers on policy semantics the annotations cannot express: results are 'evidence, not permission', missing/RETIRED answers must not be fabricated, and REFUSED/gap conditions require human review rather than customer promises.

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?

Front-loaded with what is retrieved, then immediately graduates to constraints and routing guidance. Five compact sentences carry distinct payloads, though the gap/REFUSED instruction partially restates the 'not permission' framing and could be tightened by one clause.

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 return structure need not be described, and the annotations plus description jointly cover safety and the agent's decision workflow. The remaining shortfall is the unexplained limit parameter and what 'selected' means in selection terms, but the operational picture is largely complete.

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%, so the description is the only place parameter meaning could live, yet it never explains deskId, question, or limit. 'Selected approved answers' loosely implies the limit controls how many answers are returned, but the uuid desk scoping and the question text constraints (max 500 chars) are left entirely implicit.

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?

Specific verb and resource: retrieves selected approved answers for a customer question plus the desk's approved refund rules, commitments, and escalation limits. This aggregated bundle is clearly distinguishable from siblings like search_approved_answers, list_refund_rules, and list_escalation_limits, which each return a single artifact class.

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?

Explicit routing: 'Call evaluate_commitment before promising a refund, feature, or timeline' names the alternative and the triggering condition. It also states the fallback behavior (draft for human review when tools fail, return gaps, or REFUSED), which tells the agent when not to proceed.

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