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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds genuinely non-structured context: this is a fixed, operator-curated watchlist that cannot be modified through the API, entries are annotated with last-checked and freshness state, and adding a tender requires contacting a human. That is real behavioral disclosure beyond the 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 short sentences, all front-loaded and load-bearing: what the list is, what each entry contains, and the one thing an agent might otherwise try to attempt through the API. Nothing is wasted.

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 carries the burden of explaining return content, and it does so (tenders plus last-checked and freshness fields). It omits ordering, list size, and whether stale entries are still returned, which would matter for interpreting freshness output.

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 tool takes zero parameters, so the baseline is 4. The description adds no parameter meaning, but none is needed, and it correctly implies no filtering or pagination arguments exist.

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 names a specific resource — the TED tenders on Aurelmark's watchlist — and states what each entry carries (last-checked time, data freshness). It is clearly a read of a curated watchlist rather than a general tender search. It does not explicitly distinguish itself from the sibling get_tender_deadline_changes, which an agent could easily confuse this with.

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 mention that additions happen by emailing the address in /docs usefully tells the agent this list is read-only-with-an-out-of-band-write-path. However, there is no guidance on when to call this versus get_tender_deadline_changes, which is the natural alternative for deadline data.

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