Skip to main content
Glama

Rate places

rate_places
Destructive

Save a rating model as one of the user's searches and score it: a model with a name creates a search; a model with the id and version of a search refines it, overwriting its model (replace: true is needed for a search this conversation did not create); an id alone scores that search as saved. Returns where it is saved, with a link to open it in the app, and the top places with a per-criterion breakdown. Adds the model's new locations to the user's saved locations.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "rate_places"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoa saved search: alone, scores it as saved; with model, saves the model over it
nameNothe search's name, e.g. Safe suburbs near Cincinnati; required for a new search, renames one given by id
limitNohow many top places to return, default 25, at most 100
modelNothe model to save and score
replaceNotrue only after the user agreed to overwrite a search this conversation did not create; a version from get_rating_model, or from scoring a saved search, needs it
versionNowith id and model: the version the last rate_places or get_rating_model returned

Output Schema

NameRequiredDescriptionDefault
searchYes
resultsYes
scored_placesYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.3/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing that refining overwrites the existing model, that `replace` guards overwrites of searches this conversation did not create, and that rating/saving appends the model's new locations to the user's saved locations. That side-effect disclosure is the key non-obvious behavior for a destructive write tool. What it omits is scale/error behavior, e.g. what happens when a version is stale.

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?

Front-loaded with the core action, then the mode rules, then the return values — a sensible order. It is packed into long semicolon-chained clauses with nested parentheses, which is dense but every clause carries information; only light trimming is possible.

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?

For a complex six-parameter tool with nested model objects, the definition covers the mode logic, the destructive-overwrite guard, side effects on saved locations, and the return shape (link plus top places with per-criterion breakdown, even though an output schema already exists). The remaining gap is operational edge cases such as stale versions or invalid model columns.

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 the baseline is 3, but the description adds cross-parameter semantics the schema cannot express: which combinations of `id`, `name`, `model`, and `version` produce create vs. overwrite vs. score. Those combination rules are the main source of misuse risk and are spelled out in prose.

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 concrete verb and resource ("Save a rating model as one of the user's searches and score it") and then immediately distinguishes the three operating modes — create with a name, refine with id+version, score with id alone. An agent can tell exactly what this tool does and how it differs from read-only siblings like get_rating_model or list_rating_models.

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

Usage Guidelines4/5

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

Gives explicit conditional routing among its own modes and a real precondition for `replace` ("true is needed for a search this conversation did not create"). It does not state when to prefer this over search_places or compare_places, but for a save-and-score tool the mode rules are the operative guidance and they are clear.

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