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

Annotations declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered, but the description adds zero behavioral context on top of that. It discloses nothing about pagination defaults, type-specific filter behavior (e.g. penalty params filtering only enforcement cases), or conditional parameter relationships. The description neither contradicts nor meaningfully extends the annotations.

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?

A single sentence, front-loaded with the verb and resource, then a colon-separated list of document types—zero wasted words. The structure is efficient, though the brevity trades away the behavioral and usage guidance that a 14-parameter tool would benefit from; it is concise rather than merely under-specified.

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?

This is a high-complexity tool—14 parameters, no required fields, conditional requirements (min_date/max_date require both type and date_kind), and type-specific behaviors (statutes cannot be date-filtered; penalty amounts only filter murs/adrs). The description omits all of this. The rich schema compensates substantially and an output schema exists, but for a tool this complex the one-line description does not adequately preview the conditional logic an agent must navigate.

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% with detailed per-parameter notes (notably the date_kind enum's per-type documentation and the conditional 'admin_fines is slow' caveat), so the baseline of 3 applies. The description itself adds no parameter-level meaning, but the schema fully compensates, so no penalty is warranted.

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 specific verb ('Search') and resource ('FEC legal documents') and enumerates the document categories (advisory opinions, MURs, ADRs, administrative fines), clearly delimiting its scope. This separates it cleanly from the sibling search tools (candidates, committees, contributions, expenditures, filings), which operate on entirely different content 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?

The document-type list implies when to use this tool (for legal/advisory/enforcement documents) versus the candidate/committee/expenditure search siblings, but there is no explicit when/when-not guidance or named alternatives. Some operational guidance exists in the schema (e.g. 'admin_fines is slow without a query or respondent filter'), but the description itself carries none of it.

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