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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description does add useful behavior beyond them — a per-session cap of 20 queries — but it is internally contradictory on cost, stating '0.01 USDC/query' and then 'FREE preview — no key, no payment', which leaves an agent unsure whether this call is billed.

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 text is padded with marketing boilerplate and a leading checkmark emoji, and the 'no key / free / no payment' point is repeated twice in different words. Front-loading is poor: the actual subject of the tool is buried in the second sentence behind a price line.

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, so the description carries the burden of explaining what a preview returns — it says only 'public metadata only' in the schema and nothing in the description about response shape or what 'preview' excludes versus a paid query. For a tool whose whole value is a free taste of a listing, that gap matters.

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 100% and the schema already explains both `slug` (defaults to the routed session's listing) and `question` (free text, echoed back). The description's 'sample questions' line gestures at the `question` parameter but adds no format or length guidance beyond the schema, so baseline 3 applies.

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 identifies a concrete subject ('pubmedwatch: new PubMed biomedical papers') but never states the verb of the tool itself — it reads like listing ad copy rather than 'returns a free preview of a listing.' It is also hard-coded to a single listing despite a `slug` parameter, so an agent must infer from the annotation title ('Preview Data Listing (Free)') what the tool actually does.

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 an implied 'try free before paying' posture, but no explicit when-to-use rule and no routing to siblings such as data_session_query or data_session_open, which are the obvious alternatives for actually querying this data. The sample questions hint at usage but do not tell the agent when this tool is the correct choice over a paid session.

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