telos.proof

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

With no annotations, the description carries the full burden and does step up on the safety profile: it declares read-only, zero-auth, and 'no external side effects beyond local subprocess reads.' That is genuinely useful. It stops short of disclosing idempotency, error behavior, or what a local subprocess read implies operationally.

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 when-to-use clause is sensibly front-loaded, but the middle sentence is a comma-chained jargon inventory ('source refs, context refs, route, admission, side effects, output digests, verifier checks, and the Emet witness stage') that adds bulk without clarifying scope. It is not bloated, but it is not tight either.

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-arg, no-annotation, no-output-schema tool, the description does confirm the return is a JSON proof packet and states the safety profile. What it omits — how this differs from the three sibling proof tools and what the witness/admission stages mean — leaves real gaps against the family's complexity.

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?

The tool takes zero parameters, so there is no parameter semantics to document and the baseline is 4. The description does not fabricate or contradict any argument contract.

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 recognizable resource ('agent-action proof packet') and lists the artifacts it joins, so the general intent is clear. However, no sibling is distinguished — telos.proof.research, telos.proof.visual, and telos.proof.build likely operate in the same space, and the heavy jargon ('Emet witness stage', 'route, admission') obscures what uniquely defines this variant.

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 'Use when a host needs...' clause gives an implied trigger context, which is more than nothing. But there is no when-not guidance, no named alternatives, and no distinction drawn from the telos.proof.* siblings, so an agent given a proof request cannot tell which of the four to pick.

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