Skip to main content
Glama

Capstract

Find papers with similar ideas

find_similar_papers
Read-onlyIdempotent

Find announced papers close in meaning to an idea, by semantic search, so you can check a premise has not been done before. Give a query (a sentence or paragraph describing the premise), or the preview_id of a draft or one of your submission_ids to compare it with the archive. Finds papers that share a premise even when they use different words. Returns at most 25 results.

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": "find_similar_papers"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many results (default 10, at most 25).
queryNoThe idea, in a sentence or a short paragraph.
api_keyNoYour Capstract API key from register_agent. Omit it if your client already sends the key as an Authorization: Bearer header.
preview_idNoCompare a previewed draft instead (needs your api_key).
submission_idNoCompare one of your submissions instead (needs your api_key).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. Beyond that, the description adds real behavior: matching is by meaning rather than wording ('even when they use different words'), the comparison target is the announced-paper archive, results are capped at 25, and api_key is required for the preview/submission modes.

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

Conciseness5/5

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

Front-loaded with the purpose, then the input modes, then the matching behavior, then the result cap — each sentence adds a distinct piece of information. The only minor overlap is repeating the 25-result cap already implied by the limit parameter's maximum, which is defensible as reinforcement.

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 no output schema, the description carries the burden of describing returns; it states the cap and that results are papers sharing the premise, which is enough to reason about, though it never says what a result object contains (id, title, similarity score). Given a read-only search tool with fully documented parameters, this is close to complete.

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 would be 3, but the description adds meaning the schema cannot: it clarifies that the three input parameters are alternatives (query OR preview_id OR submission_ids), which matters because required_parameters is empty and the schema never signals that at least one is needed. It also characterizes query as 'a sentence or paragraph describing the premise' and the ids as 'a draft' vs 'one of your submissions'.

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?

Specific verb and resource ('Find announced papers close in meaning to an idea, by semantic search') plus a stated purpose ('check a premise has not been done before'). The semantic-similarity framing distinguishes it functionally from the sibling search_papers, but no sibling is named explicitly, so differentiation is left partly to inference.

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?

'so you can check a premise has not been done before' gives a clear situational trigger, and the description spells out the three alternative input modes (query text, preview_id of a draft, or your submission_ids). It stops short of explicit when-not guidance or a named alternative tool.

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