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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, fully covering the safety profile. The description adds 'Anonymous and read-only,' which is redundant with the annotations. It also lists the kinds of data returned (e.g., 'English-preferred titles, buyers, countries, CPV codes'), which is helpful but does not disclose any additional behavioral traits such as pagination behavior, rate limits, or state changes. Since the annotations cover the core safety attributes, the description provides modest extra context but not substantial behavioral disclosure.

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 two sentences, front-loaded with the core purpose, then enumerates return fields and caveats. Every clause adds information—there is no fluff. It avoids redundant restatement of the tool name and is appropriately sized for a search tool.

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 search tool with no output schema, the description does a good job: it states the query nature, enumerates returned fields (titles, buyers, countries, CPV codes, lot signals, URLs, pagination metadata, source caveats), and notes it is anonymous/read-only. It could be more explicit about pagination usage (e.g., that results are paginated and how page/limit control navigation), but the schema already provides parameter descriptions and the example clarifies the query syntax. The lack of a deep explanation of the 'bounded expert query' syntax is partially mitigated by the schema example. Overall, it is fairly complete for an agent to call 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?

The input schema fully describes all three parameters: query includes a concise example and maximum length, page and limit have clear descriptions. Schema description coverage is 100%, so per the rubric the baseline is 3. The tool description itself does not add any parameter-level semantics beyond the schema; it only mentions pagination metadata in the return list, not how to use the parameters. Thus the schema carries the burden and is adequate.

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 states the tool's function: 'Search the official EU Tenders Electronic Daily (TED) corpus with a bounded expert query.' It identifies the specific resource (TED corpus), the verb (search), and the distinguishing characteristic ('bounded expert query'). It also lists the returned data fields, making the purpose unmistakable. While it does not explicitly contrast with sibling tools like ted_opportunity_radar, the specificity is sufficient for an agent to understand what it does.

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?

There is no explicit guidance about when to use this tool versus alternatives. The phrase 'bounded expert query' hints at a specialized use case, but it does not state conditions for choosing this tool over others (e.g., ted_opportunity_radar) or mention any exclusions, prerequisites, or alternative scenarios. The description only notes that it is 'Anonymous and read-only,' which is a trait, not usage guidance.

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