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

With no annotations provided, the description carries the full burden and does well: it discloses billing details (prepaid credit at GB-month rate), retention (last 3 versions, 32 slots), constraints (load ≤3 redemptions), and failure/grace behavior (credit exhaustion → 30-day read-only grace). Minor omission: does not mention whether save overwrites or creates new versions, but the retention policy implies versioning. No contradiction with annotations (none provided).

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 dense but well-structured, front-loading the core value proposition in the first sentence and then using a bullet-like flow for actions. It earns its length by covering billing, retention, and lifecycle details concisely. Slight redundancy with schema (action enum) and a few extra details could be trimmed, but overall efficient.

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?

Given the tool's complexity (4 actions, 8 params, no output schema, no annotations), the description covers essential aspects: operational flow, billing, retention, and grace behavior. It does not describe return structures (e.g., list returns metadata), but the absence of output schema shifts burden; however, the description does enough to guide basic usage. Complete for typical interaction, with minor gaps.

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 75% and the description adds value for key parameters: it clarifies that 'size_bytes' is declared for save, 'version' is used for load (pin a version), and 'slot' is required for save/load/delete. The description augments the schema by explaining the flow for save and load (upload_url, body_url), which the schema doesn't cover. However, not every parameter is explicitly tied to description context (e.g., content_type), but the high schema coverage reduces the burden.

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 identifies this as the core durable memory tool for the locker, with explicit verbs for each action (save/load/list/delete) and distinguishes it from siblings by emphasizing its role as the central storage interface. It goes beyond a simple restatement of the name and provides a comprehensive purpose statement.

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 explicitly states when to use this tool: to store state that must outlive the session, and notes that it is the primary alternative to other locker tools (e.g., locker_credit for billing, locker_nonce for nonces). It also outlines operational procedures (save requires PUT to upload_url, load returns signed body_url, etc.), making selection unambiguous.

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