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

Despite annotations covering mutation flags, the description adds substantial behavior the annotations cannot: per-call billing, the 402 challenge/payment flow, non-billing edge cases, UTC timestamps in the ICS, that agenda_ics is a one-shot file rather than a subscription, and what the response summary summarizes. The readOnlyHint=false annotation is consistent with a call that triggers billing, so nothing is contradicted.

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 most valuable facts (seven-day window, paid per call) are front-loaded, but the text repeats itself across two languages ('no account' / 'sem conta nem passe') and runs long for a four-parameter tool. Bilingual duplication costs tokens without adding information.

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 return-value burden and does it reasonably: it explains the resumo fields, the optional agenda_ics payload, and the payment-or-error outcome. Billing and failure modes are covered; pagination or response size limits are not mentioned, a minor gap for a seven-day aggregate.

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% and already documents dia as the last day of the week, slug, agenda=1, and programa as a title/category substring. The description still adds real meaning beyond the schema: programa matches case- and accent-insensitively, inputs and matches are not truncated, and agenda=1 yields UTC-timed unique events in an importable ICS.

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 opening sentence states a specific verb and resource with scope: 'Seven days of the channel's schedule that end on the requested day,' plus the paid-per-call, no-account framing. It implicitly separates this from the sibling get_api_x402_programacao_by_slug (no day window) and the free daily read, but never names either sibling, and the switch to Portuguese mid-description blurs the core statement.

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?

It gives concrete conditions: use it for agent access paid per call with no account, unpaid requests get 402 once delivery is available, and 'a leitura diária gratuita conserva os mesmos dados' points to the free daily alternative. It also states when the caller is not charged (missing channel, day, or programa; history offline). It stops short of naming which sibling tool is the free path, leaving the agent to map that itself.

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