add_memory

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

With no annotations, the description carries the behavioral burden. It discloses the durable write behavior, the category-based file path, and deduplication. It does not describe failure modes or response details, but the output schema covers the latter and the main side-effect behavior is well communicated.

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 sentences with zero filler. The core purpose, storage location, dedup behavior, and a useful invocation example are all packed into a very compact 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?

The tool is simple, has an output schema, and the description covers purpose, file location, deduplication, and parameters via example. The only notable gaps are the missing explicit mention of the default category and lack of guidance about when not to use it, but these are minor for successful 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?

Schema descriptions are absent, so the description must compensate. It partially does by providing a concrete example mapping 'fact' to a preference string and 'category' to 'Preferencias', and by showing how category influences the file path. However, it does not explain that category defaults to 'General', which is only visible in 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 clearly states the action ('Guarda un hecho duradero sobre el usuario'), the storage target ('memory/<category>.md'), and a key behavior ('sin duplicar'). The example further clarifies exactly what kind of content belongs here, distinguishing it from generic file-writing tools.

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 implies when to use the tool: when persisting durable user facts/preferences rather than writing arbitrary files. However, it does not explicitly name alternatives or exclusions, such as when to prefer write_file, append_file, or search_knowledge instead.

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