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

Beyond readOnlyHint=false and openWorldHint=true, the description discloses the cost model (one Meta call per tracked account), the latency (several seconds), the throttling window, and the exact error payload shape (429 too_soon / retry_after_seconds). It also states the side effect precisely: it writes today's snapshot that all other reads then serve.

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 lead sentence and throttle/error details are front-loaded and earn their place, but the description repeats itself: 'One Meta call per account, so it takes several seconds' is restated verbatim in 'Slow: one Meta call per tracked account,' and 'Refresh from Meta' duplicates the annotation title. Trimming the duplicate would lose nothing.

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?

For a zero-parameter, no-output-schema tool, the description covers everything an agent needs to call it correctly: trigger condition, latency expectation, throttle and error handling, request body, and the fact that it produces the data other tools read. Nothing material 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?

There are zero parameters, so the schema does the little work there is, and the description adds the one operational detail the schema can't convey: send an empty object {} as the request body. That is useful beyond additionalProperties=false, but there is no further parameter meaning to convey.

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 uses a specific verb and resource ('Pulls current numbers from Meta ... writes today's snapshot') and scopes it to the account plus every tracked competitor. It also explicitly separates itself from the surrounding read tools: 'every other Market Intel read serves the snapshots this writes.'

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?

It gives an explicit trigger ('Only call it when the stored snapshot is stale'), an explicit rate constraint (five minutes enforced between refreshes, 429 too_soon with retry_after_seconds), and implicitly names the alternative path (all other reads serve the stored snapshots). The agent knows both when to call it and when not to.

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