Criar uma demanda (trabalho para alguém)

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

The annotations only indicate that the tool is mutating and non-destructive. The description adds valuable behavioral context: it explains that doneWhen must be verifiable by another person, gives examples of acceptable criteria, and states that the agent should ask the user rather than invent criteria. It also clarifies when subtasks are appropriate. This goes well beyond the annotations.

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 description is longer than average, but every sentence serves a purpose: the first paragraph states the core function, the second gives outcome-oriented guidance, the third details the doneWhen requirement and how to handle vague requests, and the fourth clarifies subtask usage. It is well-structured and front-loaded, with no filler.

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?

Given the tool has 10 parameters and no output schema, the description provides substantial context about what a 'demand' is and how to structure key fields. It does not mention every parameter, but the schema descriptions cover those. The instruction to ask the user when details are insufficient is a key completeness element that supports correct invocation.

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?

The schema already covers 90% of parameters with descriptions, so a baseline of 3 is appropriate. The description adds extra semantic value by elaborating on 'doneWhen' with concrete examples ('um número, um arquivo, um link') and by defining when 'subtasks' should be used. It also frames 'objective' and 'deliverable' as outcome-focused rather than method-focused, which enhances the schema's meaning.

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 clearly states the action and resource: 'Registra uma DEMANDA num projeto' (registers a demand in a project). It distinguishes this as a creation tool, but does not explicitly differentiate it from the sibling tool systemtask_task_create, so it falls just short of a perfect score.

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?

The description provides strong usage guidance: it instructs the user to say what should exist, not how, and explicitly says to ask the user if the request is too vague to define a doneWhen criterion. However, it does not compare this tool with alternatives like task_create, which would help the agent choose between them.

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