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.

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

With no annotations, the description carries the full burden, and it discloses the most important behavioral trait: reported_outcome is a self-report that is never treated as the objective outcome, which comes only from episode verification evidence. That is genuinely non-obvious semantics an agent could not get from the schema. It still does not say whether repeat reports overwrite prior ones or what permissions are required.

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?

Three short sentences, front-loaded with the purpose and followed by the one caveat that matters. No filler, though the second sentence's line-broken formatting is slightly awkward rather than harmful.

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?

An output schema exists, so return values need no explanation, and the self-report caveat is well covered. However, for a 6-parameter write tool with no annotations and zero schema descriptions, leaving task_ref and the retrieved_ids vs consulted_lesson_ids distinction unexplained is a real gap.

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 description coverage is 0%, so the description must compensate, and it partly does — it enumerates the accepted values for reported_outcome and explains that episode_id links to verification evidence. But task_ref, retrieved_ids, and note are never explained, and the distinction between consulted_lesson_ids and retrieved_ids is left unstated.

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 and object pair — recording which retrieved lessons were consulted and how the task ended — which is more than a restatement of the name. It does not name either sibling (search_experience, get_episode_evidence), so it only implicitly marks itself as the write-back counterpart to those read 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?

Usage is implied rather than stated: the tool is meant to be called at task end, after lessons have been retrieved and consulted. There is no explicit 'use this when / not when' clause and no reference to the sibling tools that produce the ids this tool consumes, so the agent must infer the workflow.

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

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

With no annotations provided, the description carries the behavioral burden and does disclose meaningful traits: lexical matching behavior, the contents of each hit, verification status, evidence references, why it matched, prerequisites, cautions, and applicability flagging via version context. It still does not explicitly confirm read-only behavior or mention pagination, rate limits, or permissions.

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 description is front-loaded with the main purpose and gives practical query advice early. It is reasonably concise, though the list of hit contents is somewhat verbose given that an output schema exists.

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 description covers the purpose and some key input guidance, and an output schema exists so return values need not be fully explained. But for a 10-parameter tool with no annotations and 0% schema description coverage, leaving most parameter semantics and all sibling routing unaddressed is a clear completeness gap.

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 description coverage is 0% across 10 parameters, so the description must explain parameter meaning, but it only addresses query, current_os, and current_versions. It leaves k, mode, tool, repo_id, language, error_type, and verified_only unexplained, which is a significant gap for a 10-parameter search tool.

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 states a specific verb and resource: searching recorded experience, specifically lessons and failed episodes, for an error or task. It is clear what the tool does, but it does not explicitly distinguish itself from sibling tools such as get_episode_evidence or report_task_outcome.

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 description gives useful usage advice for the query parameter by recommending pasting the exact error line, and it explains why current_os/current_versions should be supplied. However, it does not say when to use this tool versus sibling alternatives, nor does it give conditions for when not to use it.

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