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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint=false), so the bar is lower; the description nonetheless adds real context: corpus size (35 answers), provenance (sourced line-by-line to named GOV.UK/HMRC pages), a freshness date (re-checked 7 October 2026), and the return shape. It stops short of anything like ranking or no-match behavior, which is why it is not a 5.

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?

Purpose is front-loaded in the opening clause, and the closing sentence carries the essential routing instruction. The long parenthetical date/topic enumeration is informative for a retrieval tool but makes the sentence noticeably dense, keeping it out of 5 territory.

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 still states the return shape (matching questions with short answers), the corpus boundaries and provenance, and the escalation path to get_mtd_answer. For a two-parameter read-only search tool, nothing an agent needs in order to call it correctly is missing.

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 the query parameter already carries example phrasings, so the schema does the heavy lifting. The description's topic enumeration (thresholds, deadlines, penalties, exemptions, sign-up, software) loosely maps to valid query content but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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?

Specifies the verb (search), the resource (UK Making Tax Digital answers), and the exact scope (35 answers, MTD for Income Tax), plus the topical coverage. It also names the sibling tool get_mtd_answer and what it returns instead, so the agent can distinguish the two without opening either 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?

The final sentence routes the agent explicitly: this tool returns matching questions with short answers, and get_mtd_answer must be called for full text and sources. That is a stated condition plus a named alternative, with the enumerated topics indicating what queries are supported.

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