Zovo Federal Register Digest

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavior: the 1994 coverage floor, 500 matches per watch, 1,500 total rows, five-watch cap, and XLSX/ICS/CSV download outputs. It does not say what happens when the row cap is hit (truncation vs. error), which would have completed the picture.

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?

Two sentences, front-loaded with the usage trigger, then limits, then exclusions. Every clause carries a distinct fact (triggers, caps, formats, exclusions) with no restatement of the tool name or title.

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, return values need no explanation, and the description supplies the operational envelope an agent needs (coverage window, caps, formats). It lacks only a pointer to the sibling for follow-up retrieval and any note on behavior at the row limit.

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 a 3 is the baseline, but the description adds constraint semantics not visible in structured fields: the five-watch ceiling and the match/row limits per query. It does not clarify how `date_basis` interacts with the `date_from`/`date_to` defaults, which the schema hints at but never fully explains.

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 states a concrete verb+resource (search Federal Register documents) and bounds the domain (documents from 1994 onward, 1-5 watches). It implicitly separates itself from non-federal sources, but never names the sibling show_federal_register_documents, so an agent must guess which of the two to call for viewing results.

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 explicit trigger phrasings ('federal register this week', 'proposed rules comment deadline tracking') plus negative guidance ('Do not use for state registers or legal advice'). The one gap is that no alternative tool is named as the fallback route.

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

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds value beyond that by disclosing the delivered formats (XLSX, ICS, CSV) and that invalid or missing numbers are reported per item rather than failing the whole batch.

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?

Two sentences, usage trigger front-loaded before the exclusion, no filler. The middle clause 'download XLSX, ICS and CSV with published dates' is slightly awkward phrasing but still carries real information about outputs.

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?

An output schema exists, so return-value detail is not needed, and the description covers trigger, exclusion, batch size and output formats. For a single-parameter read tool this is sufficient, with only the sibling differentiation left thin.

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?

With 100% schema description coverage on a single array parameter, the schema already documents the 1-50 cardinality, the item format and the per-item error behavior. The description's 'one to fifty numbers' restates the schema rather than adding syntax or format meaning, 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?

States a specific verb and resource (look up federal register document numbers) plus the concrete outcomes it serves (regulatory digest, effective dates, comment periods). The phrase 'known document numbers' implicitly separates it from the search-oriented sibling find_federal_register_documents, but the sibling is never named.

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?

Opens with an explicit 'Use this when...' trigger listing the user intents it serves, and closes with a clear 'Do not use for unpublished agency guidance or legal advice' exclusion. It stops short of naming the alternative tool or the condition that selects it, so routing between this and find_federal_register_documents is still inferred.

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