company_memory_propose_from_evidence

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

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Create a candidate semantic memory' does convey a mutation-like action and the 'candidate' wording hints the memory may be provisional, but it does not disclose side effects, approval/review flow, permissions, or whether the memory is persisted immediately. This is a significant gap for a tool that likely creates state.

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 single sentence is grammatically efficient and front-loaded with the core action. However, it is under-specified for a 14-parameter operation, and the conciseness comes at the cost of essential context such as evidence versus non-evidence flows or required parameter semantics. It is not tautological, but it is closer to under-specification than to well-rounded concision.

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 complex: 14 parameters, no annotations, no output schema, and no parameter descriptions. The one-sentence description leaves an agent without enough information to construct a valid call, understand the candidate memory lifecycle, or know how evidence_id relates to registered artifacts. This is far from complete.

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%, and the description names none of the 14 parameters. It does not explain what evidence_id, memory_type, statement, title, or the defaulted fields mean, nor does it clarify which parameters are required in context. The description provides no value beyond the raw schema field names.

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 states a specific verb and resource: 'Create a candidate semantic memory' is clear, and the modifier 'citing an existing registered artifact' adds a meaningful scope. It is distinguishable from the sibling company_memory_propose by the evidence-citing precondition, though it does not explicitly name or contrast any sibling.

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 a precondition—that an existing registered artifact must be cited—but it gives no explicit when-to-use or when-not-to-use guidance. It does not mention alternatives like company_memory_propose or trusted_memory_propose or explain what should happen when no artifact evidence is available.

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