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

Annotations already establish read-only, idempotent, and non-destructive behavior, so the description does not need to repeat those. It adds meaningful context beyond the annotations by explaining that the tool uses 'two explainable signals' and that it 'does not predict awards or allege fraud,' which sets honest expectations about the tool's analytical scope. There is no contradiction with annotations.

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?

Three sentences, each earning its place: the first states the core function and signals, the second lists filters, and the third bounds expectations. The most important information is front-loaded, and there is no verbose or redundant phrasing.

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 combination of a well-described schema, safe annotations, and a clear description covers most of what an agent needs to select and invoke the tool. The main gap is that with no output schema, the description does not preview what a result entry contains, but for an opportunity-finding read tool this is not a blocking omission.

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 baseline is strong. The description adds value beyond the schema by defining the two signal enum values in plain terms: 'contracts with reported end dates in a chosen window' for renewal and 'award results reporting zero received submissions' for zero_bid. It also highlights the CPV and buyer-country filters that directly map to the cpv and country parameters.

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: 'Find traceable EU procurement opportunities from official TED notices.' It further narrows the tool by naming its two concrete signals, renewal and zero_bid, and states the relevant filters (buyer country, CPV code). This clearly distinguishes it from the sibling ted_search_notices, which would handle broader TED notice searching.

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 gives a clear when-to-use context: when the agent needs traceable procurement opportunities based on renewal or zero-bid signals rather than generic TED notice search. It adds a useful boundary with 'This does not predict awards or allege fraud,' which tells the agent this tool is not for award forecasting or fraud claims. However, it does not explicitly name an alternative tool or specify when to prefer a sibling tool such as ted_search_notices.

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