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

Annotations already declare read-only, open-world, idempotent, and non-destructive behavior. The description adds useful behavioral context: it returns awarded contracts with supplier and value by default, requires no API key, and covers a specific procurement dataset. It does not mention rate limits or pagination, but the annotations lower the burden and the added context is genuinely helpful.

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 and front-loaded with the core action, then efficiently adds scope, examples, default behavior, and auth context. Each clause serves a purpose; the UK-vs-EU note and keyless statement are short and meaningful. It is long enough to be instructive without becoming bloated.

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 six-parameter, no-output-schema search tool with no required parameters, the description covers essentially everything an agent needs: domain, coverage, search targets, examples, default status rationale, auth requirements, and positioning relative to EU tenders. The schema handles parameter details, and annotations handle safety, leaving no critical behavioral gap.

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?

The schema already describes all six parameters in detail, including status meanings, date formats, limit bounds, and keyword behavior. The description adds example keywords and restates the default awarded rationale, but that rationale also appears in the schema's status description, so the incremental value over the schema is modest.

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 a full-text search tool for UK government procurement notices from Contracts Finder, with concrete keyword examples and scope. It distinguishes the tool conceptually from sibling retrieval tools by emphasizing search semantics, but does not explicitly name or contrast siblings such as find_a_tender_notice or recent_notices.

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 provides clear context for when to search—by keyword, date range, and status—and explains the default awarded status. However, it does not explicitly state when to prefer this tool over alternatives like find_a_tender_notice, recent_notices, or search_within; usage is implied rather than contrasted.

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