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

Annotations already declare read-only/non-destructive, but the description adds substantial context beyond them: retired questions are included and signaled via enabled=false, page limits and four pagination semantics, assignment values falling back to legacy name/filter tokens, and the non-obvious rule that empty prompt regions inherit scan defaults then Global while remaining saved selections rather than effective execution regions.

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?

Purpose and scope are front-loaded, and the closing sentence handles the sibling handoff. It is dense and borderline overlong for a list tool, but nearly every clause carries non-redundant semantics (retirement signaling, inheritance rules, legacy token fallback).

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 values need not be spelled out, yet the description still covers the paging envelope, filter persistence, and the distinction from result-bearing tools. Nothing needed to call this four-parameter read tool correctly is missing.

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 100%, so the baseline is 3, but the description adds real meaning: promptId narrows to a single question using the same list shape and returns an empty list when the ID is absent, and cursor must be reused with identical filters. limit is largely restated from the schema, which caps the score below 5.

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?

Opens with a specific verb+resource+scope: reading saved questions for a Site or Topic, and enumerates the fields returned (question text, category, enabled state, tags, assignments, journey stage, region). It explicitly differentiates itself from get_prompt_results by stating it does not return collected AI answers or historical snapshots.

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?

Gives explicit routing ('use get_prompt_results directly for answers, with promptId and scanId where needed'), pagination procedure (follow every non-null nextCursor, retain filters), a cache-invalidation rule (restart enumeration after editing the catalogue), and an edge-case contract (a missing promptId returns an empty list).

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