Salvar documento

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this is a write. The description adds meaningful mitigation context beyond that: overwriting keeps a .bak copy, and files are single-subject with a title on the first line. It does not say whether creating a new file fails when the path exists, or what the tool returns, which keeps it 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?

Four short sentences, front-loaded with the action and scope, then the content rules, then the overwrite mechanics. Every sentence carries information, though the title-on-first-line rule and the path example partially duplicate the schema's path description.

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 three-parameter write tool with no output schema, the description covers input semantics and the destructive-overwrite mitigation well. It leaves gaps on the result side: whether a new file versus an update is reported, what the .bak path looks like, and what happens on an invalid or conflicting path. These are minor but real omissions for a mutation 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 coverage is 67% and the one undocumented parameter, overwrite, is explained in the description including its backup side effect. The description also reinforces the path format with a concrete example ('produtos/plano-basico.md') and states the content should be a full document. This is genuine added meaning over the schema.

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 gives a specific verb pair and resource: 'Create or update a company knowledge document (Markdown or text) in the knowledge folder.' It also clarifies the expected file format and the 'one subject per file' convention. It does not explicitly name the read-side siblings (aspa_search_knowledge, aspa_read_knowledge), but the write semantics make the distinction obvious enough.

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 states the source condition clearly ('from information the user gives') and adds a strong constraint ('Never invent facts: write only what the user provided'), which is real when-to-use guidance. It also tells the agent when to set overwrite=true. It stops short of naming an alternative tool for cases where the content already exists and should be read or appended instead.

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