trusted_memory_propose

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

No annotations are present, so the description carries the burden. It discloses that the operation requires MCP write capability, persists the proposal (side effect), and enforces a rule against self-labeling user_direct. It doesn't explain governance flow, review status, or return behavior, but it provides meaningful behavioral constraints beyond the tool name.

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?

Four short sentences, front-loaded with the core purpose and write requirement; the remaining sentences each add a distinct constraint or workflow note. 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?

For an 18-parameter tool with no annotations and no output schema, this description covers only the evidence_id edge case and write authorization. It omits governance semantics, required-field meanings, and what happens after proposal. It is not complete enough for 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 0%, so the description should explain the 18 parameters, but it only clarifies evidence_id (and the source-type implication). Required parameters memory_type, title, and statement are not explained, nor are clearance/classification, JSON fields, confidence, or tenant/project scoping. This is insufficient compensation for an undocumented 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?

States a concrete action ('Propose governed memory') with the resource and governance context. It is not a tautology and names the write-capability requirement. However, it doesn't distinguish trusted_memory_propose from sibling proposal tools such as company_memory_propose or trusted_memory_review.

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?

Provides clear operational guidance: if evidence_id is omitted, the memory is stored as an agent_observation, and agents cannot self-label user_direct; it instructs to register evidence first when a stronger source type is needed. This is clear context for when to supply evidence_id, but it never states when to prefer this tool over sibling alternatives.

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