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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds behavioral nuance beyond that: it states the typical result size without member_id (~100-200 for long debate), and explicitly instructs to report empty results honestly without reconstructing quotes from training data. This is valuable additional context that aligns with and enriches the annotation profile.

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 rich but every sentence earns its place. It leads with a clear usage directive, contrasts with alternatives, outlines a typical chain, describes default behavior, and includes a critical anti-hallucination warning. It is front-loaded and well-structured, with no wasted text.

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?

The tool has an output schema, so return value details are covered there. The description covers the full usage lifecycle: when to use, how to obtain parameters (chain), default pagination-like behavior (~100-200 items), and edge-case handling (empty results, no reconstruction). It is complete for an agent to select and invoke this tool correctly.

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%, and each parameter is already thoroughly documented in the input schema (e.g., member_id is described as 'Optional integer Members API ID... regardless of which words they used'). The description reinforces these semantics but does not add new parameter-level detail beyond what the schema already provides. A baseline of 3 is appropriate.

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 clear directive: 'USE THIS TOOL WHEN you have a debate_ext_id and want verbatim contributions, optionally filtered to one member.' This specifies the verb (get), resource (contributions in a debate), and scope (optional member filter). It also distinguishes itself from text-search tools by explaining the filtering mechanism (MemberId on Items list vs. text-based search).

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 provides explicit when-to-use guidance and contrasts with alternatives: 'text-search tools (parliament_member_debates, parliament_search_hansard) filter by contribution TEXT... This tool filters by MemberId... so vocabulary doesn't matter.' It also gives a typical tool chain (parliament_find_member → search → this tool), leaving no ambiguity about invocation context.

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