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

Annotations establish a read-only, idempotent, non-destructive operation, but the description adds substantial behavioral context beyond that. It details the exact content returned: frontmatter with specific keys, verbatim text, summaries, and status, and explains how `full` adds history, votes, amendments, and documents. It also clarifies the default session resolution logic. This is valuable behavioral information not present 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?

The description is dense but every sentence contributes information. It opens with the core purpose and output, then addresses session behavior, then the `full` flag. There is no filler or repetition. It could be slightly better structured with explicit labels, but for the complexity of the tool, the length is warranted and it remains readable.

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 lookup tool with no output schema, the description provides a strong picture of the return value: the Markdown twin with key frontmatter fields, text, summaries, and status, plus the additional data from `full`. It does not cover error cases or edge scenarios, and it does not explicitly differentiate itself from all sibling tools, but the essential details for correct invocation are present. The description is sufficiently complete for an agent to use it effectively.

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 0%, so the description must compensate for the lack of parameter documentation. It does so thoroughly: `bill` is explained with multiple example formats, `session` has its default behavior and special-session naming, and `full` lists exactly what it adds. All three parameters are semantically defined in a way that lets an agent construct valid inputs without opening the schema.

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 the tool as returning a single bill or resolution by number in various formats, and specifies the output structure (frontmatter, text, summaries, status). It distinctly frames a lookup operation, differentiating from sibling tools like bills_list and bills_search which handle lists or searches. The scope is precise and leaves no ambiguity about the tool's function.

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 description gives explicit instructions on session handling: when no session is supplied, the newest regular session is used, and special sessions require naming (e.g., '2026-special'). It also explains the effect of the `full` flag. While it does not explicitly mention alternatives or exclusions, the context implies this is the comprehensive bill lookup, contrasting with more specific tools like bills_get_text. The guidance is clear enough for an agent to decide when to invoke it.

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