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

Despite annotations already declaring readOnlyHint, idempotentHint, and destructiveHint, the description adds meaningful behavioral context: it requires an Authorization Bearer token and returns setup steps without it, is cached for up to an hour, and returns the site-wide summary on every call regardless of sort. It also provides an important interpretive caveat that a late report is a fact about filing date, not a finding of wrongdoing. This goes well beyond what annotations convey.

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?

The description is long but every sentence carries useful information: output contents, the avg_lag_excess caveat, usage guidance, alternative tools, access requirements, and data freshness. It is front-loaded with the core behavior and then branches into caveats and access. A minor structural improvement would be separating the auth/access sentence from the output discussion, but nothing is wasted.

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?

For a tool with no output schema, this description is remarkably complete: it names the returned components (site-wide summary and per-member board), specifics of the member board fields, the excess-return caveat, source parity, access method, fallback behavior without a token, caching behavior, and how to get more granular member lag data. An agent has enough to correctly invoke and interpret the tool without supplemental documentation.

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% with detailed descriptions for sort and limit, so the baseline is 3. The description adds value by explaining that the site-wide summary comes back on every call whatever the sort, which affects how the sort parameter should be interpreted. It also clarifies the sort ranking is always highest first via the schema, and the description's metric name explanations align with the enum values. This extra context justifies a score above baseline.

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?

Description states a precise purpose: measuring how quickly Congress reports trades against the STOCK Act's 45-day window, with both a site-wide summary and per-member board. It clearly distinguishes itself from siblings by pointing to get_member/list_transactions for individual trade lag, and notes the same data source as coldpine.io. The verb 'reports' and the specific metrics (median lag, share late, House vs Senate) make the tool's scope unambiguous.

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?

Explicitly states when to use this tool ('who files late' and 'how late is Congress overall') and when not to use it (for one member's lag, read disclosure_lag_days in get_member or list_transactions). It also warns about the avg_lag_excess metric never being quoted without the S&P 500 comparison, which is a usage constraint an agent needs to act on. This is strong routing guidance beyond any schema.

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