memory_ratify

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

With no annotations provided, the description fully carries the burden of behavioral disclosure. It details the write path (same as 'remember'), validation that can fail, and downstream effects: memory becomes recallable, proposal removed from queue. This transparency is thorough and accurate for a mutation 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 description is a single paragraph of 4 sentences, each sentence adding unique value: core action, process details, failure behavior, and final consequence. It is front-loaded and efficiently communicates key information without redundancy.

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 lacks an output schema, and the description does not state what the tool returns on success (e.g., the memory ID or confirmation). While it explains the effect ('memory becomes recallable'), the absence of return value information leaves a gap. Additionally, it could better contextualize the tool within the broader set of sibling tools, though it adequately explains its core role.

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 100%, so the schema already documents each parameter. The description adds only a high-level reference to 'optional overrides' but does not provide new semantics beyond what 'Override the proposed...' already states. Thus, baseline 3 is appropriate.

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 ratifies a pending proposal into a real memory, using specific verbs like 'ratify', 'loads', 'applies overrides', and 'commits'. It distinguishes itself by mentioning 'proposal' and 'queue', and contrasts with 'remember', effectively differentiating it from sibling tools like memory_propose and memory_reject.

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 when to use: when a proposal should become canon. It explains that invalid proposals are refused with a typed reason and stay pending. However, it lacks explicit guidance on when not to use this tool or alternatives among siblings (e.g., memory_reject to discard, memory_propose to create a new proposal). This omission prevents a perfect score.

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