Read retained results by evidence ID and RFC 6901 JSON pointer to page arrays/strings, inspect large-object keys for deeper queries, and keep the full original on disk.
Read a retained result by evidence ID and RFC 6901 JSON pointer. Arrays and strings are paged. Large objects return keys for deeper queries; the complete original remains on disk.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| offset | No | ||
| evidence_id | Yes | ||
| json_pointer | No |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent and non-destructive semantics, so the bar is lower. The description adds real behavior: paging for arrays/strings, key-only returns for large objects, and assurance that the complete original remains on disk, which tells the agent no data is lost by paging.
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 tight sentences, each carrying distinct information (identity, paging, large-object behavior), with the retrieval mode front-loaded.
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?
No output schema exists, so the description must convey return shape, and it does: paged arrays/strings, keys returned for large objects to drive deeper pointer queries, original retained on disk. Missing only edge details like error behavior for invalid pointers or pagination defaults.
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 carries the burden. It explains evidence_id and json_pointer semantics and links 'paged' to the limit/offset parameters, compensating well. It doesn't state defaults or bounds for limit/offset, which the bare schema also lacks.
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 and resource: read a retained result by evidence ID and JSON pointer. It's clearly distinguishable from list_evidence (enumerates) and read_bytes (raw bytes), though it doesn't name those siblings explicitly.
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?
Implies usage through 'retained result by evidence ID', which suggests it follows list_evidence, but there is no explicit when-to-use or when-to-prefer-alternatives guidance (e.g., versus read_bytes for raw content).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.