memory_propose

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

No annotations exist, so the description carries the full burden. It usefully discloses lifecycle behavior ('kind=lesson... stays provisional until a human approves it', 'Only adopted items count as verified knowledge'), which goes beyond the schema. It says nothing about side effects, persistence timing, permissions, or what a proposal returns, leaving significant behavioral gaps for an un-annotated write tool.

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 core purpose is front-loaded in the first sentence, and the remaining semicolon-separated clauses are dense but each carries distinct kind semantics. There is some redundancy with the schema's verify description, which prevents a 5.

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 7-parameter tool with a nested object and no output schema, the description covers the essential model: the four kinds, how each is verified, and the adoption/provisional lifecycle. It omits relationship semantics (supersedes/derived_from) and any routing versus sibling memory tools, so it is solid but not exhaustive.

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 57% and the nested verify object already documents the per-kind shape ({command, test_files}, {file, quote}, {quote}). The description's verification sentences largely restate that schema text rather than adding syntax or format detail. Tags, title, supersedes, and derived_from get no elaboration in the description.

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 specific verb+resource ('Propose something worth remembering for future sessions') and then enumerates the four kinds (skill, fact, preference, lesson), so the agent knows exactly what the tool produces. It does not explicitly contrast itself with the siblings memory_recall, memory_correct, or memory_report_outcome, which keeps it just below a 5.

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 per-kind clauses give clear conditions for choosing each kind ('kind=skill: a reusable technique or code pattern... kind=fact: a fact about this codebase...'), effectively telling the agent when each mode applies. However, there is no guidance on when to use this tool rather than memory_correct or memory_recall, and no exclusion criteria.

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