telos.proof.research

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

With no annotations, the description carries the full safety burden and does state the key traits: read-only, zero-auth, and no external side effects beyond local subprocess reads. That is solid disclosure of the safety profile, though it omits failure modes, idempotency, and any cost/latency expectations.

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?

Two sentences, the trigger condition front-loaded ahead of the safety and return notes. The first sentence is a heavy comma-list that is hard to parse, but there is no filler or redundancy.

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 must convey the return value and does ('Returns a JSON research-claim proof packet'), reinforced by the enumerated components. It is nearly complete for a zero-param read tool, though it leaves the meaning of some packet fields unexplained.

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 the baseline is 4. There is nothing for the description to disambiguate, and the empty schema with additionalProperties:false is self-consistent with the described behavior.

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 names a specific artifact (a fixture-backed research-claim proof packet) and enumerates the pieces it joins, which distinguishes it from generic siblings like telos.proof and telos.proof.visual. However, the dense jargon ('promotion rung the verifier derives rather than trusts') makes the core verb ambiguous, and it never explicitly contrasts itself with the other proof tools.

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 opens with a trigger phrase ('Use when a host needs...'), giving implied usage context. There is no when-not guidance and no routing to alternatives, so an agent still cannot tell from this text alone whether to pick this over telos.proof, telos.proof.build, or telos.research.seed.

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