memory_add

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

With no annotations, the description carries the behavioral burden and does well: it discloses the embedding model, that content/category/source are stored, and details the auto-category construction logic. It omits duplicate-handling and return behavior, but it provides more mechanism-level transparency than most similar tools.

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?

Every sentence earns its place: the action, the storage model, the category rule, and the intended use case. It is dense but not bloated, with the core action front-loaded.

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 5-parameter write tool with no output schema or annotations, the description covers the essential context: purpose, storage semantics, category behavior, and usage. Missing return-value or duplicate/overwrite details are notable but do not prevent correct 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 coverage is only 40% (only cwd and scope have descriptions), so the description must compensate. It does explain category auto-construction, the role of content as knowledge, and that source is stored, but leaves source's format and content's structure unspecified, limiting the compensation.

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: 'Add a memory to the shared vector store'. It further distinguishes itself through the semantic embedding mechanism and 'findable by meaning, not just keywords', which clearly separates it from keyword-oriented siblings like shared_memory_set or memory_search.

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 explicitly states when to use the tool: to 'sediment cross-agent knowledge (learnings, gotchas, decisions)' that need semantic recall. It stops short of naming alternatives or explicitly saying when not to use it, so it earns a 4 rather than a 5.

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