Skip to main content
Glama
pad01g

YaCy Fork Peer-to-Peer Search

by pad01g
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Hybrid

Measure search quality

evaluate_ranking
Read-only

Measure search ranking quality by running queries with known relevant URLs, reporting precision@k, recall@k, R-precision and rank positions to compare settings.

Instructions

Run queries whose relevant result URLs you know and report precision@k, recall@k and R-precision per query and on average, plus where each relevant URL ranked. Use it to compare settings: evaluate, change a setting, evaluate again. Queries run one after another and the call ends within about 50 seconds: queries that do not fit are reported in 'skipped', so split long lists into several calls.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kNocut-off for precision@k and recall@k
casesYesqueries with their known relevant URLs (1-30)
waitMsNohow long to let other peers answer per query (global only)
resourceNo'global': ask the other peers too; 'local': only this peer's indexglobal

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.1.1
    • addedInput schema / properties / cases / description
      Added value: +"queries with their known relevant URLs (1-30)"
    • addedInput schema / properties / cases / items / properties / query / description
      Added value: +"the query to run"
    • addedInput schema / properties / cases / items / properties / relevant / description
      Added value: +"URLs of the pages that should be found for this query"
    • addedInput schema / properties / k / description
      Added value: +"cut-off for precision@k and recall@k"
    • addedInput schema / properties / resource / description
      Added value: +"'global': ask the other peers too; 'local': only this peer's index"
    • addedInput schema / properties / waitMs / description
      Added value: +"how long to let other peers answer per query (global only)"
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover read-only and open-world scope, and the description adds non-obvious behavior: sequential query execution, an ~50-second per-call budget, and that overflow queries surface in 'skipped'. This is precisely the runtime context an agent needs to size its calls.

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

Conciseness4/5

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

Front-loaded with the core action and metrics, then usage and constraints. Two sentences are dense but every clause earns its place; minor density could be trimmed but nothing is wasted.

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?

No output schema exists, so the description must cover returns — and it does, naming per-query and average precision/recall/R-precision, ranking positions, and the 'skipped' bucket. For a 4-param tool this is complete.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3. The description references metrics tied to 'k' and hints at per-query volume limits via the time budget, but does not add syntax or format detail beyond the schema.

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?

States a specific verb+resource ('Run queries... and report precision@k, recall@k and R-precision') with the exact metrics produced, making it clearly distinct from siblings like search or get_ranking_settings.

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?

Explicitly prescribes the workflow ('evaluate, change a setting, evaluate again') and gives operational guidance for long inputs ('split long lists into several calls'), which frames when to call it versus when not to.

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

Deploy Server

Other Tools