get_episode_evidence

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

With no annotations, the description carries the full burden. "Return the recorded evidence" implies a non-mutating read and it details the evidence payload categories, but it says nothing about behavior when the episode is unknown, whether evidence can be partially missing, permissions required, or cost/latency. Adequate but leaves real behavioral gaps for a zero-annotation tool.

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?

A single front-loaded sentence with the action first and the returned categories enumerated after the colon. Every listed item is substantive evidence content, not filler.

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?

The tool is simple (one required id) and an output schema exists, so return values need not be spelled out, yet the description still summarizes them helpfully. The only notable omission is how to obtain a valid episode_id and what happens on a missing episode.

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?

Only one parameter, and the phrase "for an episode" ties episode_id to an episode identifier, so the description adds a small amount of framing. However it does not say where the identifier comes from (e.g., from report_task_outcome) or its format, and schema coverage is 0%.

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 ("Return") and resource ("the recorded evidence for an episode") and enumerates the evidence categories returned (outcome, verification records, failure signatures, tool-call metadata, lessons). It does not explicitly contrast itself with search_experience or report_task_outcome, but the retrieval-by-id framing is distinct from a search or a write.

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 is only implied: the required episode_id makes clear this is a point lookup for a known episode, and the sibling names suggest search_experience is for discovery rather than direct fetch. The description never states when to prefer this over search_experience, nor any preconditions such as the episode having been recorded first.

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