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

Beyond the annotations (readOnly/idempotent/openWorld already declared), the description adds genuinely non-obvious behavior: results cached up to 10 minutes, typical 0.5-2 s latency, USD 0.005 price with no free tier, and a precise billing rule (zero matches are charged, bad input/unknown agency/outage are not). It also carries a prompt-injection warning about returned page text and on-chain strings, which is exactly the kind of safety context annotations cannot express.

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?

Purpose and return fields are front-loaded in the first two sentences, with operational metadata (cache, billing, latency, safety) after. Sentences are dense and mostly earn their place, though the billing/latency/price block is terse to the point of being run-on and the trailing docs link is unrelated boilerplate.

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 an output schema present, the description need not enumerate return values, yet it still names key fields, and it covers cost, caching, latency and untrusted-content handling for an 8-parameter open-world search. The main gap is that no guidance is given on discovering valid agency slugs or on how filters interact, and the documentation URL points to an unrelated SEC/EDGAR page, which undercuts its usefulness.

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%, so every parameter including query, agency, date bounds, type, order and comment_open is already documented in the schema; baseline 3 applies. The description adds no parameter-level meaning — its field list (docket IDs, PDF URLs, CFR references) describes output, not inputs, so it does not go beyond 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?

"Search Federal Register rules and comment periods" states a specific verb and resource, then enumerates returned document classes (rules, proposed rules, notices) and fields (comment close date, docket IDs, CFR references). An agent can immediately separate this from siblings like sec_company_lookup or treasury_yield_curve, which cover different data domains.

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 important usage caveat — "Not the official legal edition (verify against the PDF)" — and discloses charging conditions, which shape when it is worth calling. However, it never says when to prefer this over alternatives, nor does it guide filter combinations (e.g., when to add comment_open vs. a date range), leaving selection logic implicit.

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