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

Annotations declare readOnlyHint=true (agent knows it's a read operation) and openWorldHint=true. The description adds valuable behavioral context beyond annotations: the plausibility-gating thresholds ($5M income, $50M expenses), full-corpus vs sample guarantee, and that totals cover every match regardless of limit. These are genuinely behavior-defining details not in 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?

Three dense sentences, zero filler. Every sentence adds distinct information: coverage guarantee, return fields, filter options, plausibility thresholds, normalized matching. Front-loaded with the primary purpose.

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?

Completeness is strong for a 4-param search tool: full-cover guarantee, plausibility gating, filtering options, and matching behavior all covered. No output schema exists, but the description lists return contents (registrant, client, spending, issue codes, committees, totals), which compensates. No behavioral gaps identified.

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%, so the schema already documents all 4 params. The description adds meaning beyond schema: clarifies organization matching is on a normalized form with the Pfizer example, explains that totals always cover every match (independent of limit), and confirms quarter requires year. The 'limit only caps rows, not totals' nuance is important and only in the description.

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?

Clear verb+resource: 'Search Senate LDA lobbying filings from the complete corpus.' Explicitly notes full coverage ('every quarterly report (LD-2)... not a sample') and lists return contents (registrant, client, spending, issue codes, committees, totals). Distinguishes from analyze_* siblings by being a raw search tool vs analytic tools.

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?

States when to use (search filings by quarter, org, or both) and clarifies it returns raw search results. Doesn't explicitly name alternatives or state when NOT to use it (e.g., vs analyze_policy_area_ecosystem), but the analytic-vs-search distinction is implied by the tool name family and sibling names.

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