Skip to main content
Glama

What should I buy?

what_to_buy

Builds his FitCard from the shirts he owns and returns the shirts that will fit him, each in the right size, with a buy link. Also returns a link to his full card on fitcard.ai. Each size already accounts for his shirts and the fabric; a "snugger" or "roomier" note describes how that size fits.

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": {
      "my_shirts": "<my_shirts>"
    },
    "name": "what_to_buy"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many picks (default 8).
categoryNoOptional: only this kind of shirt.
my_shirtsYesShirts he owns, ideally 3-5 that fit him well. Brand, item and size only.
suit_sizeNoHis suit jacket size off the label, if he knows it, e.g. "44L" or "42 Regular". Helps with Tall sizes.
fit_preferenceNoHow he likes shirts to fit, if he said. Default standard.
dress_shirt_sizeNoHis dress shirt size off the label, if he knows it, e.g. "17 34/35" (neck, sleeve). Helps with long sleeves.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / my_shirts / items / properties / fit / description
      Previous value: -"How it fits him overall. Default \"fits\". Prefer chest and length when he says where it's off."New value: +"How it fits him overall. Default \"fits\". The chest, belly and length fields say where it's off."
  2. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, and the description is consistent with that by implying a FitCard is built (some state) while nothing is destroyed. It usefully discloses output behavior beyond the annotations — buy links, a full-card link, and 'snugger'/'roomier' sizing notes — but never says whether the FitCard is persisted server-side or ephemeral, nor whether external commerce calls are made, which matters given openWorldHint=false.

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 sentences, front-loaded with the core action and result, then the ancillary card link and an explanation of the fit notes. Nothing is padded, though the informal third-person 'his' phrasing is slightly less scannable than neutral wording.

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?

With six parameters, no output schema, and full schema coverage, the description carries the return-value burden and does so adequately by describing the picks, sizes, buy link, card link, and fit notes. The main remaining gap is the persistence/state question raised by readOnlyHint=false, which an agent might want answered before calling.

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 every parameter including the nested shirt fields is already documented, and the baseline of 3 applies. The description adds one piece of real meaning — that each recommended size already accounts for the shirts supplied and the fabric, so the agent shouldn't second-guess the returned sizes — but it does not clarify defaults or interactions between fit_preference and the per-shirt fit fields.

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?

The description states a specific verb and outcome: it builds a FitCard from shirts the user owns and returns fitting shirts, each in the right size, with a buy link and a link to the full card. That is far more concrete than the vague title 'What should I buy?'. It does not, however, distinguish itself from the siblings shirt_measurements and size_me, leaving the agent to infer that this is the recommendation step rather than the measurement step.

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

Usage Guidelines3/5

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

Usage is only implied: the tool is clearly meant to be called once the user's existing shirts are known, and the my_shirts schema note ('ideally 3-5 that fit him well') gives input guidance. There is no explicit statement of when to call this versus shirt_measurements or size_me, and no prerequisites or exclusions are named.

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