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

Goes well beyond the annotations (which only declare read-only/idempotent/non-destructive): it discloses the price (0.01 USDC), the payment rail (x402, USDC on Base or Solana, no account or API key), that invalid input is refused before payment, that failed runs are never charged, and that an unpaid call returns x402 PaymentRequired. This is exactly the operational context an agent needs before invoking a paid tool.

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 purpose, then behavior, then payment terms, then invocation pointers — a sensible ordering. It is dense but nearly every clause carries information; the trailing 'How to call it' and HTTP URL are operational pointers rather than filler. Slightly long for a 2-parameter read tool, but no sentence 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 fully carries the return-shape burden: ordered notice sequence, change-event types with their supporting notice references, and the resulting state. Combined with the payment/error behavior and the pre-2023 single-notice caveat, an agent has everything needed to call it and interpret results.

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 schema already documents both `id` (TED publication number of any notice) and `lang`. The description adds only indirect reinforcement via the example URL (?id=599727-2026) and the phrase 'from one of its notices,' which clarifies that any notice of the procedure is acceptable — a marginal but real addition. Baseline 3 applies when the schema carries the parameter burden.

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 concrete resource (the lifecycle of a procurement procedure derived from one TED notice) and enumerates the returned content: ordered notices (prior information, call, corrigenda, award, contract modification), change events, and resulting state. It implicitly distinguishes itself from a single-notice fetch by saying 'every TED notice of the same procedure,' but it never names the sibling tools (tenders_get_notice, tenders_get_changes, tenders_get_deadlines) whose territory overlaps with the events it lists.

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 prescribed: 'from one of its notices' tells the agent it can start from any notice, and 'history before eForms (2023) may hold only one notice' is a useful expectation-setting caveat. However, there is no explicit when-to-use-this-vs-alternatives guidance against tenders_get_notice, tenders_get_changes, or tenders_get_deadlines, which return overlapping data.

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