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

Annotations cover safety (readOnlyHint, idempotent, non-destructive) but say nothing about billing, and the description carries that load: no charge at quote time, HTTP 402 + Stripe shared payment token to pay, and 'charged only if the run passes its controls.' It also discloses the validation contract (a null control phrase must return 0) and what accompanies the result (stated limits, run id, dated citation line) — material behavior an agent cannot infer from structured fields.

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-loaded with what is measured, then the contract, then the payment mechanics, then the sibling relationship — a sensible order. It is dense and runs long, but each sentence carries distinct information (denominator, null control, no-charge quote, payment protocol, charge condition, pairing). Minor trimming is possible but nothing is filler.

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 description compensates by naming exactly what comes back (payment_url, price, instructions; and post-run: limits, run id, dated citation line). Combined with the disclosed charge condition and control requirement, an agent has everything needed to call this correctly and to explain the result to a user.

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 100%, including the agency enum and start/end defaults, so the baseline would be 3. The description adds genuine meaning beyond that by defining what 'phrase' is counted against (the year-by-year denominator of final and proposed rules) and by framing the agency parameter as a scoping choice. It does not walk through start/end semantics (10-year cap, 1994 floor) itself, leaving those to the schema.

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?

Opens with a concrete verb+resource+scope: 'what share of U.S. federal final and proposed rules mention a phrase, year by year, from the Federal Register, optionally for one agency.' The denominator is stated explicitly (every final and proposed rule that year), which pins down the measurement. It also names the sibling it pairs with (run_filing_trend), so an agent can place it against the alternative without opening either 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?

Gives clear operational context: the call only validates and returns a payment_url, charges nothing, and the actual run is triggered by POSTing to payment_url over MPP. The sibling note ('pairs with run_filing_trend') frames when this measurement is the right one. It stops short of an explicit when-not or an enumeration of the other run_* siblings, so it is clear context rather than full routing guidance.

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