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

Annotations already establish the safety profile (readOnlyHint, idempotentHint, non-destructive, closed-world), so the bar is lower. The description adds genuine behavioral context beyond that: core prompts carry scores while comparison prompts are reported separately, which affects how results should be interpreted. It omits pagination behavior and result size, keeping this at a 3.

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 short sentences with the resource statement front-loaded and no filler. Nothing is redundant, though the phrasing is a noun fragment rather than a self-contained statement of what the tool does.

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?

This is a paginated read tool with 6 parameters, 17% schema description coverage, and no output schema. The description omits the existence of paging (cursor/limit), the default-false active_only filter, and how the two cohorts are returned in a response, so an agent lacks the context to call it efficiently or interpret results.

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 only 17% (just the cursor param), so the description must carry the load for 6 parameters. It adds real meaning for the cohort enum by explaining core vs comparison, but says nothing about active_only, limit boundaries, prompt_set_id, or the required project_id, leaving most parameters semantically thin.

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 the resource (tracked prompts) and enumerates the payload fields (topic, intent, status), so an agent knows what comes back. It also distinguishes the two cohorts, but it never explicitly states the verb or contrasts itself with siblings like read_visibility_results or read_performance, which also surface prompt-adjacent data.

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 no guidance on when to call this versus sibling read tools, nor any prerequisite (e.g. needing a project_id or a prior paginated call). The only implicit usage signal is the core/comparison split, which hints at the cohort parameter but does not say when either branch applies.

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