Skip to main content
Glama

Stocks On Chain

Report something this site does not have

report_gap

Tell us you wanted something and did not get it: a stock we do not track, a chain a stock is not on, a field no endpoint carries, a tool that does not exist, a figure you believe is wrong, or a path that failed. Call this when another tool has just answered with a miss - the answer names the kind to send. THERE IS NO FREE-TEXT FIELD AND THERE WILL NOT BE ONE: a report is an enumerated kind plus a short subject, because the counts are what is useful and prose from an anonymous caller is a prompt-injection surface pointed at the people who read it. Nothing about you is recorded - no address, no header, no identifier - so a report cannot be joined to a caller and there is no reply. The report is counted in aggregate and returned to you with a prefilled link a human can open to track it. Reporting costs nothing and is never required.

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": {
      "kind": "<kind>",
      "subject": "<subject>"
    },
    "name": "report_gap"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesWhat was missing. One of: missing_stock (A stock this site does not track at all.) missing_listing (A stock we track, but not on the chain the caller wanted.) missing_field (A field no endpoint carries.) missing_tool (An MCP tool that does not exist.) wrong_figure (A published figure the caller believes is wrong.) broken_endpoint (A path that failed or answered in an unusable shape.)
subjectYesWhat it was about - a ticker, a field name, a tool name or a path. Letters, digits, dot, slash, hyphen and underscore, up to 64 characters. Not a sentence: there is no free-text field. A wallet or contract address is refused - send the ticker or the path instead.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

The annotations only say this is a non-destructive, open-world, non-idempotent write; the description adds genuinely non-obvious behavior: nothing about the caller is recorded (no address, header, or identifier), reports cannot be joined to a caller, there is no reply, and the result is aggregate counts plus a prefilled tracking link. The explicit rationale for refusing free text versus the prompt-injection surface is exactly the kind of context an agent cannot infer from any structured field.

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?

It is front-loaded with the action and the trigger, and the emphatic constraints are placed where they will be read before the call. Some material repeats the schema (the no-free-text rule and the address refusal appear in both), but the repetition is defensible for a policy constraint that an agent might otherwise violate.

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?

For a two-parameter tool with no output schema, the description covers what is needed: what to send, what not to send, what gets stored, what comes back (aggregate count and a prefilled link), and that no response or follow-up should be expected. Nothing essential is left for the agent to guess.

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% and the enum values are fully documented, so the mechanics are already carried by the schema and a baseline of 3 applies. The description goes beyond it by explaining why the shape is a terse enumerated kind plus short subject ("the counts are what is useful") and by reinforcing that wallet or contract addresses are refused, which discourages an agent from stuffing prose or an address into the subject field.

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 names a specific verb and resource ("Tell us you wanted something and did not get it") and enumerates the exact gap categories: untracked stock, chain not listed, missing field, missing tool, wrong figure, broken path. It is unmistakably distinct from every read-only sibling (get_stock, list_chains, search_stocks), since none of them files anything.

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 states the triggering condition precisely: "Call this when another tool has just answered with a miss - the answer names the kind to send," which tells the agent both when to invoke it and how to pick the enum value. It also sets expectation boundaries ("Reporting costs nothing and is never required"), removing any doubt about whether a call is mandatory.

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