stamp_memory

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

No annotations exist, so the description carries the full burden and does well: it discloses canonicalization (input bytes/format may change), submission of the digest to public calendars (irreversible public disclosure and a network dependency), and that nothing is stored server-side. It omits that a fresh receipt is initially pending rather than already Bitcoin-anchored, which the phrase 'proves the exact bytes existed no later than a Bitcoin block time' glosses over for an agent calling this for the first time.

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?

Three dense sentences, front-loaded with the full operation chain, then the proof claim, then the storage disclaimer. Every clause carries information; nothing is redundant padding.

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?

With no output schema, the description correctly describes the return value (memory plus base64 .ots receipt), which is the crucial missing piece an agent needs. The remaining gap is the follow-up workflow: nothing says the receipt should later be checked with verify_receipt or that anchoring is asynchronous.

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 key, tags, content, agent_id, and created_at, and the baseline is 3. The description adds only indirect meaning via 'dmt-memory/v1' canonicalization, implying content must be JSON-canonicalizable, but does not explain required fields, defaults, or how created_at interacts with the stamped proof.

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 precise chain of specific verbs and resources: canonicalize a dmt-memory/v1 JSON memory, SHA-256 it, stamp the digest on OpenTimestamps calendars, return memory plus a base64 .ots receipt. The only gap is that it never names the sibling verify_receipt, so the stamp-vs-verify split is left to inference from the name.

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 useful scope boundaries ('does not prove authorship', 'stores nothing') that tell the agent what this tool is not for, but gives no explicit when-to-use framing and never routes to verify_receipt for checking a receipt. Usage is implied by the description rather than prescribed.

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