Skip to main content
Glama

Choose the best SwishrJobs capability for a task

select_capability

Rank capabilities for a described task by task match, measured synthetic success rate, and expected cost per accepted result, and explain the ranking. Use this to decide which capability to run before quoting it. The task may be described in English, Arabic, Spanish, French, German, Portuguese, Chinese, or Japanese; this is discovery only, and every deliverable is produced in English.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task": "<task>"
    },
    "name": "select_capability"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYesThe work the caller wants done, in words. Any supported language; native scripts and transliterations are both accepted.
limitNo
available_onlyNoExclude capabilities the provider cannot run right now.

Output Schema

NameRequiredDescriptionDefault
taskYes
resultsYes
serviceNo
versionNo
languageNoHow the query was read for multilingual discovery. Present on every response; null only when multilingual matching is disabled.
ranking_basisYes
total_capabilitiesNo
excluded_unavailableNo
measured_capabilitiesNo
supported_query_languagesNoLanguages discovery accepts, with labels. Null when multilingual matching is disabled.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / task / description
      Previous value: -"The work the caller wants done, in words."New value: +"The work the caller wants done, in words. Any supported language; native scripts and transliterations are both accepted."
    • addedOutput schema / properties / language
      Added value: +{
      +  "description": "How the query was read for multilingual discovery. Present on every response; null only when multilingual matching is disabled.",
      +  "properties": {
      +    "canonical_language": {
      +      "type": "string"
      +    },
      +    "discovery_only": {
      +      "type": "boolean"
      +    },
      +    "matched_languages": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "note": {
      +      "type": "string"
      +    },
      +    "query_languages": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "script_languages": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / supported_query_languages
      Added value: +{
      +  "description": "Languages discovery accepts, with labels. Null when multilingual matching is disabled.",
      +  "items": {
      +    "properties": {
      +      "code": {
      +        "type": "string"
      +      },
      +      "label": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "code",
      +      "label"
      +    ],
      +    "type": "object"
      +  },
      +  "type": [
      +    "array",
      +    "null"
      +  ]
      +}
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does real work: it declares 'this is discovery only' (no execution), enumerates the eight accepted input languages including transliterations, and warns that every deliverable is produced in English. It stops short of stating auth requirements, rate limits, or determinism of the synthetic-success measurement.

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?

Three dense sentences, front-loaded with the ranking action and criteria, then the workflow hook, then the language/English-deliverable caveat. No filler, though the language list is the longest element and could have been compressed.

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

Completeness4/5

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

An output schema exists, so return values need not be explained; the description covers discovery-only scope, language handling, and ranking rationale. The main residual gap is the undocumented 'limit' parameter and the absence of any guidance on what happens when limit is 0.

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 coverage is 67%, with 'task' and 'available_only' documented but 'limit' entirely undocumented in both schema and description. The description's language enumeration adds meaning beyond the schema's vague 'any supported language', but it says nothing about limit semantics or the default-5 behavior.

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

Purpose4/5

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

States a specific verb and resource ('Rank capabilities for a described task') plus the three ranking criteria (task match, synthetic success rate, cost per accepted result). It is clearly distinct from the submit_* family, though it never names the nearest sibling list_capabilities, so the agent must infer that boundary.

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

Usage Guidelines4/5

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

'Use this to decide which capability to run before quoting it' gives a concrete decision point in the workflow. No explicit when-not or named alternative (list_capabilities, get_performance) is offered, so the exclusion is implied rather than stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources