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

Annotations already establish readOnlyHint, idempotentHint, and openWorldHint, but the description adds substantial behavioral context beyond them: official profiles survive unavailable enrichment, ballots come newest first, votesSession defaults to the member's latest session, and oversized limits cap with a notice. These details materially affect how an agent should invoke and interpret the tool.

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 well front-loaded: the core read operation and identifier source come first, followed by fallback behavior and paging controls. Every sentence carries operational information, and none is redundant against the title or schema.

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?

With rich annotations, full schema coverage, and an output schema, the remaining burden is behavioral guidance. The description covers identifier selection, enrichment fallback, ballot-source behavior, session defaults, paging, and limit caps, leaving no material gap for correct invocation.

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%, so the baseline is 3, and the schema already documents parameters thoroughly. The description still adds useful cross-parameter guidance: pass exactly one identifier, use zero limits for profile-only lookup, and remember votesSession and votesBillCode require an official personId.

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 opens with a specific verb and resource: 'Read one House MP' identified by slug or official personId. It also distinguishes the tool from sibling search tools by naming canparl_search_members.detailLookup as the source of identifiers, so an agent can tell what this tool is for without inspecting the schema.

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?

It explicitly says to pass exactly one identifier from canparl_search_members detailLookup, explains the fallback between official House data and OpenParliament enrichment, and describes when recent ballots come from each source. It also tells the agent how to get profile-only results by zeroing out the bill and ballot limits.

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