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

Annotations already cover safety and idempotency, and the description adds non-obvious traits: every fact carries a source, the dataset has a hard recency boundary, and the tools "do not certify that any claim is true." That trust/coverage framing is real value beyond the annotations; it stops short of describing result shape or how limit interacts with the total record.

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 first sentence is a single ~110-word run-on with deeply nested clauses enumerating data columns, which hurts scannability despite being front-loaded with the core purpose. Nearly all content is relevant, but it would read far better as a short purpose line followed by bulleted data scope and caveats.

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 does the work of explaining what comes back — release date plus source, prices read on a stated day, tiered access availability, flagship/free-plan answers — and covers the freshness boundary. What is missing is shape-level detail (single list vs. grouped per lab, how limit caps results), which for a 7-optional-param read tool is a minor gap.

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 parameter descriptions are unusually thorough (e.g. on_free_plan's unknown/unnamed/restricted edge case). The description restates the filter set at a high level but adds no syntax or semantics the schema does not already carry, so the 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?

States a specific verb and resource — The Durability Curve's record of AI model releases from ten named labs — and enumerates the exact facts returned (release dates, API list prices with read dates, Access Gap availability, flagship price and free-plan answer). Against siblings like get_claim_ledger, get_essay and get_weekly_calls the resource is unmistakable, so an agent can select it without opening the schema.

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?

"Search by model or lab name, or filter by lab, release date, frontier status or free-plan access" gives concrete calling patterns that map onto the query/lab/date/frontier_only/on_free_plan parameters. The freshness caveat ("runs to data_through; a newer release is not in it yet") is a useful when-not signal, but no sibling alternative or exclusion is named.

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