Skip to main content
Glama

Add the person's own figures

submit_figures

Send what the person pays and earns where they live to Borgo's open community data (published rounded under CC BY 4.0, no name or address kept; an automated review holds amounts far from others' or the official figure). Without confirm it sends nothing and returns the draft with its privacy note: show both to the person. Call again with confirm true only after they said yes to these exact figures, and only figures they gave you as their own, never estimates or figures read on another site. The answer carries a removal code for them to keep.

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": {
      "city": "<city>"
    },
    "name": "submit_figures"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityYesCity id (turin-it) or name ('Turin', 'Palermo, IT')
rentNo
pricesNoWhat they pay for everyday things, in the place's currency
ratingNoLiving there, all things considered, 1 poor to 5 excellent
salaryNo
confirmNotrue only after the person agreed to send these exact figures
currencyNoISO 4217; must be the place's own (checked)

Output Schema

NameRequiredDescriptionDefault
reportVersionYesThe report's shape version (now 2.0)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: publication under CC BY 4.0 with rounding, no name or address retained, an automated outlier/official-figure review, a two-step draft-then-confirm flow, and a removal code in the response. This is unusually complete disclosure for a publicly writing tool whose destructiveHint is 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?

Four dense sentences, front-loaded with the action and its privacy/licensing consequences, and each sentence carries a distinct obligation. Parenthetical stacking makes some sentences heavy, but nothing is filler.

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?

Output schema exists, so return values need not be spelled out, yet the description still flags the draft-with-privacy-note case and the removal code, which are the non-obvious returns. The main gap is idempotency: with idempotentHint=false, it never says what happens if the same figures are submitted twice.

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 71%, so the schema carries most field-level meaning, but the description adds real semantics on top: confirm is gated on explicit user consent to these exact figures, and every figure is constrained to be the person's own rather than an estimate or a number seen elsewhere. It does not add detail on the city, currency, or nested rent/salary structure 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?

States a specific verb and destination: send the person's pay and rent figures to Borgo's open community data, published rounded under CC BY 4.0. The effect (anonymized public dataset entry with automated review) is clear enough to separate it from reading siblings like community_figures and from remove_figures without opening either 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?

Gives explicit when-to-use and when-not: without confirm it only drafts and returns the privacy note to show the person, and confirm true may be sent only after they agreed to these exact figures. It also excludes estimates and figures read on other sites, which is exactly the boundary an agent would otherwise cross.

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.