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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial context on top: detection is rule-based on sender domain, subject pattern and fixed phrases with 'no language model', bodies are truncated at 20,000 characters, nothing is stored and the usage record holds counts only, and unmatched emails are still listed by position.

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 definition is a single dense paragraph with the core action front-loaded in the first clause, and each subsequent sentence carries distinct information (detection method, return fields, truncation, storage, auth). It is long, but little of it is filler.

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 no output schema, the description must describe the return payload, and it does so thoroughly: match type, matched signals, booking reference, dates, flight number, stations/airports, times, amounts, confidence, deadline hint, and a pre-filled Untap check with missing arguments listed. An agent has everything needed to interpret 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?

Schema coverage is 100% so the single parameter is already documented; the description nevertheless adds meaning beyond the schema by restating the email fields and clarifying the 20,000-character body read limit, which the schema's 200,000 maxLength does not convey.

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?

States a precise verb and resource ('Reads up to 25 emails ... and picks out the ones that point to a train, flight or TfL claim') and enumerates the claim categories it detects. This clearly separates it from the sibling add_*/check_*/list_* tools that act on already-identified claims.

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?

Usage is implied rather than stated: the agent can infer this is the detection step that feeds save_claim, and 'No sign-in needed' hints at its standalone nature. However, no sibling is named and there is no explicit when-to-use/when-not guidance (e.g., versus check_train_delay or list_my_claims).

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