lembrar

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

With no annotations, the description carries the full load and does disclose the key non-obvious behavior: the entry is later injected into `contexto_projeto` when a similar task occurs, which is the effect an agent most needs to know. It omits append-vs-overwrite semantics, deduplication of near-identical entries, and any size or storage limits, so it stops short of full behavioral coverage.

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 short sentences, each doing distinct work: purpose and record kinds first, downstream effect second, writing style with an example third. It is front-loaded and free of 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?

An output schema exists, so return values need not be described, and the persistence effect is covered. However, for a 3-parameter mutation/creation tool with zero schema documentation and no annotations, the unexplained required `pasta` parameter and the absence of duplicate-handling guidance leave real gaps.

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 0%, so the description must compensate. It partially does: `tipo` values are implied ('decisao' default, 'erro'), and `texto` gets content guidance with a concrete example format ('erro: X falhava por Y; resolvido com Z'). The required `pasta` parameter is never explained — no hint whether it is a project path, a folder name, or a memory namespace.

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: 'Guarda uma decisão do projeto ... ou um erro', and names the two record kinds ('decisao', 'erro') that map to the `tipo` parameter. It also distinguishes itself from the read-side sibling by naming `contexto_projeto` as where the stored item resurfaces, so an agent can separate this write tool from retrieval tools without opening either schema.

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 clear usage context: record a project decision or an error plus its fix, so the information is available later for similar tasks. It does not state exclusions — for example versus `indexar_projeto`, `ler_relevante`, or general note-taking siblings — but the 'decision or resolved error' framing is specific enough to route most calls correctly.

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