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

Beyond the read-only/idempotent annotations it adds real context: requires auth, is free, returns results 'newest change first', paginates at '20 a page', and surfaces submission states (pending/rejection). It stops short of describing the row contents or pagination totals, but it is consistent with the annotations.

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-loads what the tool is, but the rest is a dense run-on of semicolons and parentheticals mixing usage, id semantics, and parameter docs. It is not bloated, yet its structure makes it hard to scan.

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?

With no output schema, the description carries the return-shape burden and does reasonably: one row per unit, ordering, and page size. Auth, filtering, and pagination are covered; only row field details and total counts are absent.

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 must carry the parameter burden, and it largely does: 'query matches a title, or an id or slug exactly; kind narrows to units or datasets'. The page parameter is only implied via '20 a page', so it is not fully specified.

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 resource and scope: the operator's own knowledge units (one row per unit) and datasets, newest change first. It distinguishes itself from the mutation siblings by naming revise_knowledge, set_knowledge_price, retire_knowledge and update_dataset, but never clarifies how it differs from list_datasets, which plausibly overlaps.

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 a clear context: 'Use it to find the ids of what you sold — to price, revise or retire a unit, or edit a dataset', plus using it to check pending/rejection state. That is solid routing to downstream tools, but it offers no explicit when-not guidance or named alternatives for overlapping siblings.

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