Skip to main content
Glama

Agentic Keychain

by com.agentickeychain
OverviewDiscussionsAdmin

Compare capabilities

compare_capabilities
Read-onlyIdempotent

Assess two to five named capabilities side by side for the same inputs, with the same method and ak.offer.v1 offer shape as evaluate_capability. Use when: you already hold a shortlist of capability ids and want each one's decision, reasons and offer in one answer. Not for: finding candidates (search_capabilities) or a single capability (evaluate_capability). Input: the capability ids, plus the optional task, model, expected_runs, baseline_cost_estimate_usd, context and constraints that evaluate_capability reads. Output: ak.comparison.v1 with the results ranked by decision, lower-bound net saving, relevance and capability id, each with its reasons and an ak.offer.v1 offer.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskNoPlain description of the task you are about to do (at most 4000 characters).
modelNoThe model you run on, e.g. claude-sonnet-5. Savings are reported only for measured models.
contextNoFacts about your situation, keyed by the capability's parameter names (e.g. log_lines).
constraintsNoLimits you set for the answer; a capability outside them is reported as blocked, with the reason code.
capabilitiesYesTwo to five capabilities to compare, each as an id, ak:// URI or slug.
expected_runsNoHow many times you expect to perform this kind of task.
baseline_cost_estimate_usdNoWhat one run of this task costs you today without the capability, in USD.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / capabilities / description
      Added value: +"Two to five capabilities to compare, each as an id, ak:// URI or slug."
    • addedInput schema / properties / constraints / description
      Added value: +"Limits you set for the answer; a capability outside them is reported as blocked, with the reason code."
    • addedInput schema / properties / constraints / properties / max_cost_usd / description
      Added value: +"The highest price in USD you accept; a capability priced above it is blocked (over_max_cost)."
    • addedInput schema / properties / constraints / properties / minimum_confidence / description
      Added value: +"The lowest confidence in the measured saving you accept, from 0.5 to 0.999 (default 0.9); below it the answer is blocked (below_minimum_confidence)."
  2. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false). The description adds real behavior beyond that: it shares the same method and offer shape as evaluate_capability, returns a ranked result set, and surfaces blocked entries with reason codes. It does not discuss cost/latency of running the comparison, which is a minor gap.

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 the action, then Use when / Not for / Input / Output in a tight sequence. Every sentence carries routing, input, or return information; no filler.

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?

There is no output schema, so the description correctly supplies the return contract: ak.comparison.v1, ranked by decision, lower-bound net saving, relevance and capability id, each with reasons and an ak.offer.v1 offer. Combined with 100% schema coverage on seven parameters, an agent has everything needed to call and interpret it.

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 baseline is 3. The description exceeds it by clarifying that the optional task, model, expected_runs, baseline_cost_estimate_usd, context and constraints are exactly those evaluate_capability reads, giving the agent cross-tool semantic consistency. It adds no per-parameter syntax 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?

The first sentence states a precise verb (Assess), resource (capabilities), cardinality (two to five), and scope (same inputs, same method/offer shape as evaluate_capability). It explicitly distinguishes itself from search_capabilities and evaluate_capability, so an agent can route without opening any schema.

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?

It gives an explicit 'Use when' trigger (holding a shortlist of ids and wanting decision, reasons and offer in one answer) and an explicit 'Not for' with the two named alternatives for the excluded cases. Nothing about when to select this tool is left to inference.

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

All Agentic Keychain toolsInspect
Try in Browser
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources