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

Annotations already cover the read-only, non-destructive, closed-world profile, yet the description adds substantial beyond-schema behavior: downsampling to a maximum of 26 points, model omission under half its answers, the historyWindow shortening flag, competitorLimit default and cap, and the precise definition of visibility vs. share of voice. It also specifies the `{ ok: false, error }` failure shape and instructs the agent not to blindly retry, which is exactly the operational context annotations cannot convey.

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 output-semantics content is front-loaded and useful, but the description is dense and runs long, blending return-shape definitions, metric caveats, and error-handling instructions into a single block. Sentences like the one about recommendation criteria and factual errors being read from answer text are tangential to invoking the tool correctly.

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?

There is no output schema and the tool is complex, so the description carries the return-value burden itself — and does: it names the history, promptHistory, and historyWindow fields and explains downsampling and omission rules. Combined with the documented error path, an agent has everything needed to call and interpret the result.

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 only 60%, and the description compensates usefully: it explains promptId's origin (get-llm-monitoring config.prompts[].id) and clarifies competitorLimit semantics ('keep more than the default 4'). advertiserProjectId and the two analytics parameters are left to the schema, but the agent-critical parameters are covered.

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?

States a specific verb and resource with scope: 'Get one saved prompt's scores across completed monitoring runs, oldest first.' The agent can distinguish this retrieval tool from siblings like get-llm-monitoring (config) and get-llm-prompt-suggestions because the description explicitly points to get-llm-monitoring as the source of promptId.

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 an explicit trigger: 'Use this when the user asks how a prompt is trending or progressing,' and routes the agent to get-llm-monitoring for obtaining promptId. It lacks explicit when-not guidance or a named alternative for adjacent tasks (e.g., config vs. history), so it stops short of a 5.

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