Skip to main content
Glama
Sign In

Kaiku

by tech.kaiku.mcp
OverviewDiscussionsAdmin

List claims

list_claims
Read-only

A project's claims, each with its label (what a paper's \label and a citation name it by, e.g. 'thm:d5-rank5'), its number, its statement (Markdown with formulas), its status and what it rests on. A project writes them on one of two scales, answered as 'scale' with its 'statuses' and 'kinds': 'math' — theorem, lemma, proposition, corollary, conjecture, question; 'open' (not proved), 'paper' (proved on paper), 'computer' (by a computation), 'lean' (formalised in Lean), 'refuted', 'retracted' (taken back — the † of a result) — or 'law' — position, conclusion, risk, obligation; 'draft', 'agreed', 'practice' (confirmed by practice), 'disputed', 'outdated' (the norm under it changed). set_claim_scale chooses it. A basis is a wiki page with the proof ('page', its id and title — or 'hidden' where you may not open the page), a computation by the name a [comp:…] cites ('computation'), a Lean declaration ('lean'), a source in words ('source') or a norm of law ('legal': the act on the legal shelf — 'legal.document', its id for get_legal_document, its title and the 'place' cited — with 'changed' true when the act's publisher has said other words since, 'reaches' whether the change is in the place cited (null where that cannot be told), 'changedAt', and 'asOf' — when the text it rests on was received, its edition; a person marks it looked at on the register's screen). This register is where a claim's status is kept: read it here rather than from a page's words, and change it with set_claim_status. Ordered by number, then label. Anybody who sees the project.

Input Schema

NameRequiredDescriptionDefault
qNoWords its label, number, title or statement holds, case aside.
kindNoOnly claims of this kind, one of the project's scale.
statusNoOnly claims of this status, one of the project's scale.
projectYesThe project key, e.g. MATH.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"Only claims of this kind: theorem, lemma, proposition, corollary, conjecture, question."New value: +"Only claims of this kind, one of the project's scale."
    • changedInput schema / properties / status / description
      Previous value: -"Only claims of this status: open, paper, computer, lean, refuted, retracted."New value: +"Only claims of this status, one of the project's scale."
  2. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish read-only, closed-world, non-destructive behavior. The description adds useful context beyond that: ordering by number then label, access scope ('Anybody who sees the project'), and the meaning of hidden basis pages and legal-change fields. It omits pagination or result-size limits.

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

Conciseness2/5

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

The description is a dense run-on that spends most of its length enumerating statuses, kinds, and basis fields. Much of that detail belongs in set_claim_scale, get_claim, or the legal document tools, and the core 'list claims with these filters' message is buried.

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?

Because there is no output schema, the description must explain the return shape, and it does: label, number, statement, status, basis, plus scale-specific statuses and kinds. It is nearly complete for a read-only list tool, missing only pagination or limit behavior.

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 schema already documents q, kind, status, and project. The description still adds value by explaining that kind and status are drawn from the project's scale and by enumerating the math and law scales and their statuses, which helps an agent choose valid filter values.

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?

The description makes clear this returns a project's claims with their label, number, statement, status, and basis. It distinguishes the tool from page prose and from set_claim_status, though it never explicitly says 'list' or contrasts with get_claim.

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?

It explicitly says to read claim status here rather than from a page's words, and to change status with set_claim_status. That gives clear usage context, but it does not distinguish list_claims from get_claim or say when a filtered listing is preferable to fetching one claim.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Kaiku toolsInspect
Try in Browser
Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources