add_memory

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

With no annotations provided, the description fully carries the behavioral transparency burden. It discloses important traits: mandatory source fields with consequences of missing provenance, scope-based retrieval filtering, and deduplication making replay harmless. This provides substantial insight into how the tool behaves.

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 a single dense paragraph of three sentences, each carrying essential information about purpose, constraints, and behavior. It is slightly verbose but every sentence earns its place 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's complexity (7 parameters, 4 required), the description covers purpose, usage guidelines, parameter semantics, and key behavioral traits without relying on external annotations or an output schema. It lacks only an explicit explanation of return values, which is not expected for a write operation without an output schema.

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?

Although schema coverage is 100%, the description significantly enriches parameter understanding. It explains why source and source_date are mandatory, clarifies valid kind values and explicitly excludes learned_rule/anti_pattern, and describes how scope filters retrieval. This goes well beyond the schema's field descriptions.

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 tool writes a memory entry with a specific verb and resource ('Ecrit une entree dans la memoire de l'utilisateur'), making its purpose unambiguous. It differentiates from sibling tools by framing it as the entry point for the second brain, distinct from visualization, lead generation, and publishing 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 gives clear usage context: it is for knowledge the user has that Publiar hasn't seen ('ce que tu sais et que Publiar n'a pas vu passer'). It also explicitly refuses certain kinds (learned_rule, anti_pattern), indicating when not to use those. However, it does not explicitly name alternative tools for those cases.

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