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

Annotations already cover readOnly/idempotent/non-destructive/openWorld=false, so the bar is lower; the description still adds real context: the privacy boundary ('never the memory itself'), the chained/citable nature of rows, and that an empty result is a valid outcome. It does not detail rate limits or the auth-proof exchange, but the per-parameter schema covers the auth mechanics.

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?

Front-loaded with the dual access modes and the row contents, then the use case and the alternative tool, then edge cases. Dense and largely waste-free, though the trailing 'Read-only' is redundant with readOnlyHint=true and 'Empty is allowed' is dropped in without connective framing.

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?

An output schema exists, so return-value detail is not required, yet the description still names the row fields. It covers both auth paths, the sibling alternative, the privacy limit, and empty results. Adequate for an agent to call correctly; remaining gaps (nonce acquisition flow) are carried by the schema.

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 100%, so the baseline is 3, but the description adds cross-parameter logic the individual schema fields only state piecemeal: 'by did, or your own with proof and no did,' which tells the agent the did/proof inputs are mutually exclusive operating modes rather than independent knobs.

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 ('Reads a citizen's public seal history') and immediately delimits scope: public seals only, keyed by did or by proof for one's own. It explicitly disambiguates from the sibling stamp_check and implicitly from seal_memory via 'never the memory itself.' An agent can tell what this returns (digest, kind, label, public claim) without opening the schema.

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?

Gives both the primary use case ('verify a citizen's memory seals') and an explicit alternative with its selecting condition ('For anonymous stamps use stamp_check'), plus the two access modes (with did vs. with proof and no did). Edge behavior is called out ('Empty is allowed'), leaving little to inference.

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