Skip to main content
Glama

Change criteria roles / proof

edit_search_spec
Idempotent

Before the run (status ready): change the role of criteria (required = must be proven, plus = a bonus) and how strictly they are proven (inference = may be inferred, explicit = needs an explicit source; dearer), and the order of the sources. No AI call; the estimate is counted again. Needs a plan (or credits). [REST: PATCH /api/tasks/{id}/spec]

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_id": "<task_id>"
    },
    "name": "edit_search_spec"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idYesThe search id (task id), e.g. from list_searches or create_search.
versionNoThe spec version from get_search (optional: protects against an edit made meanwhile in the web).
criteriaNo
source_orderNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Goes beyond the annotations by disclosing that no AI call is made, that the cost estimate is recomputed, and that a plan or credits are required. Annotations already carry the mutation/idempotency profile, and the description does not say what happens to downstream results or what a stale-version conflict returns. Useful additions, but not rich behavioral coverage.

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-loads the state precondition, then the three editable aspects, then operational facts, in a single dense paragraph with no filler. The parenthetical glossary style is compact but slightly telegraphic.

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?

For a non-destructive, idempotent mutation with no output schema, it covers the state gate, the credit/plan requirement, and the cost-recount side effect. It omits what the response returns after the re-estimate and how partial criteria updates behave, which are the remaining gaps.

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 50%, and the description supplies the missing meaning for the two most consequential enums: required = must be proven, plus = a bonus, inference = may be inferred, explicit = needs an explicit source and is 'dearer'. It also frames source_order's purpose. It adds nothing on version beyond what the schema already says.

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 set: change the role of criteria (required vs plus), the proof standard (inference vs explicit), and the order of sources. The scope is unmistakable and the field-level detail beats a generic 'edit' description. It does not distinguish itself from the sibling edit_criterion, so an agent must infer the split, keeping it below 5.

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?

Gives a clear state precondition ('Before the run (status ready)') and a prerequisite ('Needs a plan (or credits)'), which is real when-to-use guidance. It does not name an alternative for editing the same fields after a run has started, so there is no explicit when-not path.

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