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

The readOnlyHint annotation already covers the safety profile, and the description adds meaningful context beyond it: the internal structure of the proof (Merkle path, day root, chain hash) and the offline verification path. It also implies the run must be finished for the proof to exist. This is useful behavioral context, with no contradiction of the annotation.

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 totaling roughly 30 words, with the core purpose front-loaded and zero filler. The first sentence defines the deliverable and its contents; the second provides the actionable verification pointer. Every sentence earns its place.

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 simple read-only tool with a single parameter and no output schema, the description covers the essential ground: it lists what the proof contains (serving as the return-value description) and how to verify it offline. Minor gaps remain — the source of run_id and behavior for unfinished runs — but both are reasonably inferable from 'proof of a finished run.'

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 0%, with only an undocumented required run_id string, so the description carries the documentation burden. It partially compensates by establishing that the proof concerns 'a finished run,' making it clear run_id refers to that run's identifier. However, it never explicitly names or explains the parameter, its format, or how an agent might obtain a valid run_id.

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 clearly identifies the resource — a tamper-evident proof bundle for a finished run — and enumerates its contents (hashed record, Merkle path, day root, chain hash, OpenTimestamps status), which distinguishes it from siblings like runvouch_status and runvouch_runs. However, the primary action verb is implicit; it never explicitly states whether the tool generates, retrieves, or returns the proof.

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?

Usage context is implied: 'proof of a finished run' signals the tool is for completed runs and the verification workflow is described via 'verify offline with templates/verify_proof.py.' However, no sibling tools are named and there is no explicit statement of when to choose this over runvouch_status or runvouch_runs, leaving tool-selection guidance to inference.

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