Skip to main content
Glama

Mastering Financial Markets

Review a public user proposal

submit_peer_review
Idempotent

Prepare an evidence-based peer review for the separate 15-day User Register after explicit user publication consent. The author is publicly masked. Financial records and official audits remain unchanged. A proof-pending receipt is not yet public acceptance.

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": {
      "user_requested_submission": "<user_requested_submission>",
      "public_consent": "<public_consent>",
      "request_id": "<request_id>",
      "parent_id": "<parent_id>",
      "model_id": "<model_id>",
      "position": "<position>",
      "explanation": "<explanation>",
      "source": "<source>"
    },
    "name": "submit_peer_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceYesOfficial verification source: URL of the filing and the table, line and column read.
model_idYesIdentifier of the AI model actually used for the review (a model id, not the app name); MFM does not verify it.
positionYesCONFIRM_WITH_EVIDENCE, REFUTE_WITH_EVIDENCE or INCONCLUSIVE.
parent_idYesId of the user proposal being reviewed (from list_user_proposals or fetch "user-proposal:<id>").
request_idYesStable UUID v4 across retries.
explanationYesThe checks performed and their result, 20 to 12,000 characters.
public_consentYesMust be true: the user agreed that the review appears in the public User Register with masked email and hash prefix.
user_requested_submissionYesMust be true, and only after the user explicitly asked to publish this review.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / properties / explanation / description
      Added value: +"The checks performed and their result, 20 to 12,000 characters."
    • addedInput schema / properties / model_id / description
      Added value: +"Identifier of the AI model actually used for the review (a model id, not the app name); MFM does not verify it."
    • addedInput schema / properties / parent_id / description
      Added value: +"Id of the user proposal being reviewed (from list_user_proposals or fetch \"user-proposal:<id>\")."
    • addedInput schema / properties / position / description
      Added value: +"CONFIRM_WITH_EVIDENCE, REFUTE_WITH_EVIDENCE or INCONCLUSIVE."
    • addedInput schema / properties / public_consent / description
      Added value: +"Must be true: the user agreed that the review appears in the public User Register with masked email and hash prefix."
    • addedInput schema / properties / source / description
      Added value: +"Official verification source: URL of the filing and the table, line and column read."
    • addedInput schema / properties / user_requested_submission / description
      Added value: +"Must be true, and only after the user explicitly asked to publish this review."
  2. First observed

TDQS

B3/5.0
Behavior3/5

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

Annotations already declare non-read-only, non-destructive, idempotent, open-world. The description adds genuinely new context: the author is publicly masked, and financial records and official audits are left unchanged (scoping the side effects). It also hints at a receipt state, but leaves unclear what permissions are needed or what a caller receives back.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, purpose front-loaded, but the text is dense with undefined internal vocabulary and the closing sentence ("A proof-pending receipt is not yet public acceptance") is cryptic rather than informative. Several sentences could be sharpened or cut.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

All 8 parameters are covered by the schema and there is no output schema, so the definition is broadly sufficient to call the tool. However, for a public, open-world write operation it never explains what happens after submission or what the caller gets back, which is the main open question an agent would have.

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 one of the 8 required parameters is already documented in detail (request_id UUID stability, parent_id sourcing, source format). The description adds essentially nothing beyond restating the consent condition already in the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The verb+resource is present ("Prepare an evidence-based peer review" for a user proposal), but "Prepare" sits awkwardly against the tool name submit_peer_review, and the object is obscured by unexplained jargon ("the separate 15-day User Register"). Nothing in the text distinguishes this from nearby siblings such as submit_feedback or request_update.

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?

A precondition is stated ("after explicit user publication consent"), but that same constraint is already enforced by the schema's const:true booleans, so it adds little routing value. There is no statement of when to choose this over submit_feedback/request_update, and no when-not guidance.

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