CongressMCP-full

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It successfully documents API constraints (250 result limit for 'API compliance', date format ISO 8601) and notes sub-amendment relationships, but fails to disclose safety characteristics (read-only vs destructive), rate limits, error handling patterns, or pagination behavior beyond the offset parameter existence.

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 structurally organized with clear sections but suffers from verbosity and repetition—operations are listed multiple times (in CORE OPERATIONS summary and again in categorized lists). The 'Args' and 'Returns' sections largely replicate schema information. The front-loaded marketing language ('Comprehensive Amendments Tool') wastes space that could clarify behavioral constraints.

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?

Given the tool's complexity (11 parameters, 7+ distinct operations via the operation parameter) and lack of annotations, the description provides minimum viable coverage. It leverages the existence of an output schema to avoid detailing return formats, but misses operational context such as authentication requirements, error scenarios, or the hierarchical relationship between amendment operations (e.g., that details requires type/number from search results).

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?

The schema has 0% description coverage (titles only), but the description effectively compensates by documenting 9 of 11 parameters with specific semantics: congress (118/119 examples), amendment_type (hamdt/samdt enums), date format (YYYY-MM-DDTHH:MM:SSZ), limit constraints, and sort options. It notably omits descriptions for 'format' and 'offset' parameters, leaving gaps in the parameter documentation.

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 clearly identifies this as an amendments-focused tool and enumerates seven specific operations (get_amendments, search_amendments, etc.) with their functions. It distinguishes from siblings like 'bills' or 'members' by focusing exclusively on amendment legislative data, though the 'comprehensive' framing slightly obscures that this is a monolithic router tool rather than a single operation.

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?

While the description lists available operations grouped by category (Search, Details, Process, Content), it provides no guidance on when to use specific operations versus others (e.g., get_amendments vs search_amendments) or prerequisites for operations requiring specific IDs. No alternatives or exclusions are mentioned to help the agent decide against using sibling tools like 'bills' for related legislative data.

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