New EU tenders since last check (alert)

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

With no annotations, the description carries the full burden and does the most important job: disclosing that this tool is stateful and keeps state in a local file keyed by alertName. That is a non-obvious, high-impact trait an agent could not infer from the schema. It omits what the first call returns, whether state is durable across sessions, and whether results are ordered or deduplicated across different filter combinations.

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?

A single sentence with no filler, and the differentiating trait (state-based deduplication via alertName) is front-loaded. Nothing to trim.

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 an 8-parameter, unannotated, no-output-schema tool, this covers the critical stateful behavior but leaves real gaps: what a first call (no prior state) returns, whether filters must stay constant between calls for the delta to be meaningful, and the shape of the returned notices. Adequate but short of complete.

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 75%, and the description compensates for the notable gap: alertName has no schema description, and the description explains exactly what it does (scopes the persisted state). It adds no detail on the other seven parameters, but those are documented in the schema.

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 specific behavior: returns only TED notices not returned by a previous call with the same alertName. The delta/stateful nature is unambiguous. It stops short of naming the sibling ted_search_tenders as the non-alert alternative, so the agent must infer the distinction from the name alone.

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: 'previous call with the same alertName' hints that repeated calls with a stable alertName yield new notices. But there is no explicit when-to-use, no mention of when to prefer ted_search_tenders for a full search, and no guidance on alertName reuse or first-call behavior.

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