wit_unlink

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

There are no annotations, so the description carries the full burden of behavioral disclosure. It does disclose that this is a write operation requiring confirmation ('Escrita: write + confirm') and that the relationship index is resolved at write time. However, it does not explain side effects, permissions, reversibility, or what confirmation actually entails, leaving significant behavioral gaps.

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 very short and front-loaded with the primary action. The second sentence is compact and adds relevant write/confirm context, though 'Escrita: write + confirm' is cryptic enough that it may confuse rather than clarify. Still, there is no wasted prose.

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 7-parameter write tool with no annotations and no output schema, this description is under-specified. It does not explain how the target link is identified (via url, targetId, or rel), what confirm means in practice, what expectedRev controls, or what the agent should expect after success. The only non-obvious context is the relationship-index resolution note, which is itself vague.

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 only 29%, so the description must compensate, but it barely does. The phrase 'resolvendo o índice da relação' gives some meaning to relationship resolution, and 'write + confirm' touches on confirm, but id, url, targetId, and expectedRev are left unexplained. Required parameters like id and rel are not semantically elaborated beyond their raw schema definitions.

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 opens with a specific verb and resource: 'Remove um link de um work item' (remove a link from a work item), so the core action is unmistakable. It is distinguishable from sibling tools like wit_link and wit_update, though it does not explicitly name them. The extra phrase about resolving the relationship index adds nuance but does not obscure the purpose.

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 clearly communicates the context for use: an agent should call this when a link needs to be removed from a work item. It does not explicitly compare itself to wit_link or state exclusions, so it falls short of a 5, but the intended usage is directly inferable from the verb and object.

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