Montar e disparar uma requisição customizada ao SIGAA

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

With no annotations provided, the description carries the full burden and discloses substantial behavior: automatic JSESSIONID cookie attachment from the current session, raw HTML return, and extraction of the new javax.faces.ViewState with an instruction to feed it into the next request's formFields. It does not cover error behavior (non-2xx responses, redirects, expired sessions) or warn that arbitrary POSTs can mutate server-side state, which keeps it one step from a 5.

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 sentences with zero waste: capability first, then the concrete use case, then return value and state protocol. Every sentence earns its place and the most decision-relevant information (scope, session cookie, dedicated-tool exclusion) is front-loaded.

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 a complex 5-parameter arbitrary-request tool with no output schema and no annotations, the description covers scope (restricted to sigs.ufrpe.br), session handling, return value (raw HTML + ViewState), and the ViewState refresh workflow — essentially compensating for the missing output schema. The gaps are error handling and a mutation-safety note for POST, both worth mentioning for a raw-request tool.

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 description coverage is 100% — url, method enum, referer, formFields, and contentType each already have meaningful descriptions. The schema even documents the ViewState requirement in formFields. The description adds only the state-refresh workflow ('atualize seu próximo formFields com esse valor'), which is marginal value over the schema, so the baseline 3 applies.

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 verb and resource: 'Monta e envia uma requisição HTTP arbitrária (method + url + campos de formulário) contra qualquer URL sob sigs.ufrpe.br'. It also distinguishes itself from the sibling getter tools by positioning as the escape hatch 'quando não existe uma tool dedicada para essa ação', so an agent can tell it apart from sigaa_get_notas or sigaa_download_file without inspecting schemas.

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?

Gives an explicit trigger condition: use to 'reproduzir uma ação JSF descoberta ao inspecionar o HTML' (e.g., a 'jscook_action' or 'jsfcljs' found in an onclick attribute). It also provides the when-not: 'quando não existe uma tool dedicada', implying the specialized siblings should be preferred — explicit routing that leaves nothing to inference.

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