get_agenda

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: chronological ordering and that recent already-overdue items are returned rather than excluded. It does not disclose the lookback window, whether results are capped/paginated, or any auth/scope requirements, which matter for a zero-parameter read.

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?

Two short sentences, front-loaded with what the tool returns and the ordering, with the caveat about overdue items second. No filler; the only weakness is that the second sentence spends its words on an action the schema cannot support.

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?

The output schema covers return values, so the description needn't explain them, and for a simple zero-param read it covers content, ordering and overdue inclusion. What is missing is the relationship to sibling tools (get_tarefas, get_avaliacoes, get_calendario_academico) and the scope/window of 'recent' overdue items.

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?

Zero parameters normally gives a baseline of 4, but the description introduces 'dias_restantes' as something to 'use to filter', which reads like a parameter and is not one. The parenthetical 'negative = passed' is genuinely useful output-field semantics, but the framing creates false affordance rather than resolving schema ambiguity.

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 content type (tasks and assessments with dates), ties it to a known portal block ('Minhas atividades'), and specifies chronological ordering, which distinguishes it from the bare list siblings get_tarefas and get_avaliacoes. It stops short of naming those siblings as alternatives, so the boundary must be inferred.

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 does say overdue items are included, which is a useful when-reading note, but the only explicit usage instruction is to 'use dias_restantes to filter' — and the tool has zero parameters, so no server-side filtering is possible. An agent could waste a call attempting a filter that does not exist, or misread an output field as an input.

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