Fetch a review session's saved evidence, status, and exact next step to resume revision work without losing context.
Read a Review Session, retained evidence, status, and exact next action.
| Name | Required | Description | Default |
|---|---|---|---|
| review_session_id | Yes | Process-local or persisted Review Session identifier. |
| Name | Required | Description | Default |
|---|---|---|---|
| found | Yes | ||
| message | Yes | ||
| session | No | ||
| process_local | No |
Changes observed during successful MCP inspections.
v10.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is established. The description adds value by specifying exactly what data is retrieved (retained evidence, status, exact next action), which goes beyond the annotations. No contradiction.
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 zero redundancy. The verb and core deliverables are stated immediately, making it highly efficient and easy to parse.
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 one parameter and an existing output schema, the description covers the essential information: what is read and what is returned. It does not mention error cases or prerequisites, but those are likely handled by the schema and output structure. Minor gap: it could state that the session must already exist, but this is acceptable.
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 100% and the sole parameter review_session_id is already well-documented as 'Process-local or persisted Review Session identifier.' The description adds no further parameter information, so it meets the baseline 3 without exceeding it.
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 ('Read') and resource ('Review Session') and lists the returned content (evidence, status, next action). It clearly distinguishes from sibling review tools that start, evaluate, or modify sessions, though it does not explicitly name any alternative.
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?
No when-to-use guidance is provided. The description does not mention prerequisites, alternatives, or exclusions. It is only implied that this tool is for retrieving review session data, but an agent gets no direction on when to pick this over similar getters or state-changing operations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.