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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds the behaviors an agent actually needs: amended tenders return the latest version with `updated_from_outdated: true` and `changed_since_link`, the knowledge block distinguishes known / not stated / not_extracted / pending, and the degraded case where no documents were readable returns only publication fields. It stops short of describing size or pagination, but for a single-record read that gap is minor.

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?

Front-loaded with the payload summary, then edge cases, then disclaimers, with no filler sentences. It is dense and long for a one-parameter read, and the closure over knowledge states and third-party text makes it slightly sprawling, but every sentence carries operational meaning.

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?

Covers the input source, the amendment/deadline-change behavior, the status labelling, the meaning of the knowledge block states, the degraded no-documents case, the provenance caveat on third-party text, and the Hebrew-language expectation — everything needed to call it and read the output correctly. The output schema exists, yet the description still equips the agent to interpret it rather than parse it blind.

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 lone parameter already documents type, length, and format. The description goes beyond the schema by adding the value's provenance — it must be a tender page URL from a prior search_tenders or list_my_feed result, or the slug — which prevents an agent from fabricating an identifier.

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?

Opens with a specific verb and resource ("Get one tender from Tendy") and immediately enumerates the payload: what is being bought, deadlines, eligibility thresholds, requirements, budget/fees, set-asides, size fit, next-steps brief, and documents. It is clearly the single-record fetch distinct from search_tenders and list_my_feed, which it names as the source of its input.

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?

States where the `tender` value comes from (a search_tenders or list_my_feed result URL, or its slug) and gives an explicit escalation rule: "for a detail they leave out, search_tender_documents for this tender before reporting it as missing." It also tells the agent how to interpret amended, cancelled, closed, and archived tenders rather than simply returning them.

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