metrecept-opensource

Cache: List cache entries

metrecept_list_cache_entries

List cache-tree entries to inspect cached call metadata and get digests for eviction; returns request digest, model, token count, byte size, and TTL remaining, not prompt/response content.

Instructions

List entries cached in one tree: request digest, model, token count, byte size and TTL remaining. Metadata only; never returns prompt or response content. Use it to inspect a tree or to get the digest that metrecept_evict_cache_entry needs. Get tree ids from metrecept_list_cache_trees. Page through with offset = previous offset + limit until fewer than limit entries come back. Read-only, not billed, live. Requires a Metrecept API key (METRECEPT_API_KEY env on stdio, or Authorization: Bearer on remote HTTP); results are scoped to that key's tenant only.

Input Schema

Name	Required	Description	Default
`limit`	No	Entries per page, 1-100 (clamped server-side; default 25).
`offset`	No	Zero-based offset into the tree's digest index; add limit to page forward (default 0).
`tree_id`	No	Cache tree id from metrecept_list_cache_trees (default "main").	main

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.3.1Oct 25, 2026

addedInput schema / properties / limit / description

Added value: +"Entries per page, 1-100 (clamped server-side; default 25)."

addedInput schema / properties / offset / description

Added value: +"Zero-based offset into the tree's digest index; add limit to page forward (default 0)."

addedInput schema / properties / tree_id / description

Added value: +"Cache tree id from metrecept_list_cache_trees (default \"main\")."

Addedv0.1.4Oct 25, 2026

TDQS

A4.9/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so: read-only, not billed, live, metadata-only with an explicit guarantee that prompt/response content is never returned, plus auth mechanics (METRECEPT_API_KEY env vs Bearer) and tenant scoping of results. These are exactly the traits an agent needs before calling a cache-inspection tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with what is returned, then the non-disclosure guarantee, then usage and paging, then auth. Every sentence is actionable; nothing is repeated from the schema beyond what is needed for context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return structure need not be restated, and the description still covers the two things structured fields cannot: the metadata-only privacy guarantee and the auth/tenant scoping model. Pagination and cross-tool workflow are fully specified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% so the baseline is 3, but the description adds real meaning beyond the schema by explaining the offset/limit relationship as a paging algorithm and clarifying that the digest is the join key to eviction. The tree_id default and semantics are left to the schema, so it is not a full 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ("List entries cached in one tree") and immediately enumerates the returned fields (digest, model, token count, byte size, TTL remaining). It is clearly distinguished from siblings by naming metrecept_list_cache_trees as the id source and metrecept_evict_cache_entry as the consumer of the digest.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use cases (inspect a tree, obtain a digest for eviction) plus the precondition for tree ids and a concrete pagination loop ("offset = previous offset + limit until fewer than limit entries come back"). An agent has no inference left to make about sequencing.

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