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

With no annotations, the description carries the full burden and does disclose meaningful behavior: it refuses non-profession records, requires local signing, accepts only the attestation, and forbids sending private keys. These are concrete operational and security constraints an agent must honor. It stops short of describing auth requirements, idempotency, or the response, which keeps it below a 5.

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 instruction is front-loaded in the first sentence, followed by rationale and constraints. The Deuteronomy 19:15 citation earns its place by explaining the multi-witness threshold, though the '[CHECK · internal]' prefix is dead weight.

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 no-annotation, no-output-schema tool, the description covers the workflow, refusal behavior, and the key security rule, but leaves gaps: it doesn't say what the tool returns, whether authentication is required, or how it relates to the nearby attest_record/witnesses/verify tools. It is adequate but not complete for a nested-object signing tool.

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 50%: attestation is documented in the schema, but content_hash has no description. The description partially compensates by explaining the relationship between the two ('sign its content_hash... submit only the attestation'), clarifying that content_hash is what gets signed and attestation is the output of signing.sign_seal. That added relational meaning is real but not enough to fully cover the undocumented parameter.

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 gives a specific verb (bear witness / sign) and resource (someone's sealed profession of faith) and clarifies the mechanism (sign content_hash, submit attestation). It is distinguishable from siblings like profess, attest_record, and self_attest, though it never explicitly names them. The cryptic '[CHECK · internal]' tag adds noise rather than clarity.

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?

It states the workflow (sign locally via signing.sign_seal, submit only the attestation) and the negative condition (refuses any record that is not a profession), which is useful implied guidance. However, it never says when to choose this over attest_record, witnesses, or self_attest, and gives no prerequisites for the caller.

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