Ysaere

Entity Classify

classify_entities

Classify candidate strings into company, person, technology, investor, product, funding_round, market, trend, or NOT_AN_ENTITY. Use this to type raw names before KYB or an intelligence run. Do not use it to verify a company (kyb_verify) or write a memo (quick_brief / sourced_brief). Pass target (one name + optional context) or candidates (1–20 {name, context?} objects); candidates wins if both are set. Sync — returns {results: [{name, type, confidence, reasoning}], credits_charged} immediately, not a run_id; do not poll. Costs 2 credits after a usable batch; empty input returns results=[] and charges 0. Does not create, delete, or overwrite user data; it only labels strings and may debit credits. Informational labels only — not verified fact.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "classify_entities"
  }
}

Input Schema

Name	Required	Description
`target`	No	Single name to classify (1–200 characters). Ignored when candidates is provided. Required unless candidates is set.
`context`	No	Optional disambiguating context for target (max 2000 characters). Used only with target; with candidates, set context on each item instead.
`candidates`	No	Batch of 1–20 candidates, each {name, context?}. Takes precedence over target when both are set.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedNov 12, 2026

addedInput schema / properties / candidates / description

Added value: +"Batch of 1–20 candidates, each {name, context?}. Takes precedence over target when both are set."

addedInput schema / properties / candidates / items / properties / context / description

Added value: +"Optional disambiguating context for this candidate (max 2000 characters)."

addedInput schema / properties / candidates / items / properties / name / description
```
Added value: +"Candidate string to label (1–200 characters)."
```

addedInput schema / properties / context / description

Added value: +"Optional disambiguating context for target (max 2000 characters). Used only with target; with candidates, set context on each item instead."

addedInput schema / properties / target / description

Added value: +"Single name to classify (1–200 characters). Ignored when candidates is provided. Required unless candidates is set."

First observedNov 10, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Goes well beyond the annotations: synchronous execution, concrete return shape {results, credits_charged}, no run_id and no polling, cost of 2 credits, zero charge on empty input. It also reconciles the readOnlyHint=false annotation by explaining that no user data is created or overwritten but credits may be debited. Minor gap: no note on failure/partial-batch behavior or what happens if credits are insufficient.

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 purpose and exclusions, and every clause carries information; nothing is filler. It is, however, a dense semicolon-chained block that is harder to scan than it needs to be – splitting the cost/return contract from the usage rules would improve it.

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?

For a 3-parameter credit-charging classifier with no output schema, the description supplies the return shape, cost model, sync-vs-poll behavior, input precedence, and a non-mutation guarantee. An agent has everything needed to call it correctly and interpret the response.

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 target, context, and candidates are already fully documented, including the precedence rule ("Takes precedence over target when both are set"). The description repeats that precedence rather than adding new meaning such as batching strategy or context-quality tips. Baseline 3 applies.

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 and resource ("Classify candidate strings") and enumerates the full label set including NOT_AN_ENTITY, so the output space is unambiguous up front. It also distinguishes itself from kyb_verify, quick_brief, and sourced_brief by name.

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?

Explicit positive guidance ("use this to type raw names before KYB or an intelligence run") plus explicit exclusions naming the two alternatives for verification and memo writing. The agent needs no inference to pick this tool over a sibling.

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

All Ysaere tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?