Skip to main content
Glama

Set claim

set_claim
Destructive

Add a claim to a project's register, or change one — its kind, label, number in the paper, title, statement or bases. A claim is named by 'id', or by 'project' and 'label': one that does not exist yet is created (with 'statement'; 'status' says how far it is proved from the start, 'open' if left out, and 'reason' on what ground). An existing claim's status is NOT changed here — use set_claim_status, so the journal says why. A field left out keeps its value; 'bases' given replaces the whole list. Write the statement in Markdown with $…$ formulas. The label is the paper's \label: a letter, then letters, digits and ':', '.', '_', '-' — once per project, case aside; 'newLabel' renames it. Members of the project who may write only.

Input Schema

NameRequiredDescriptionDefault
idNoThe claim to change, as list_claims returned it. Or name it by 'project' and 'label'.
kindNoOne of the project's scale (list_claims answers its 'kinds'): theorem, lemma, proposition, corollary, conjecture or question on 'math'; position, conclusion, risk or obligation on 'law'. A new claim is the scale's first — a theorem, a position — unless said.
basesNoWhat it rests on, as a JSON array replacing the list: [{"kind":"page","page":477,"note":"§3"},{"kind":"computation","ref":"kimmy/gap/m74r5u"},{"kind":"lean","ref":"D5.rank_five","repo":"ispacex/d5"},{"kind":"source","ref":"Gupta 1990, Thm 2"},{"kind":"legal","document":31,"place":"Article 6(1)(f)"}]. A page is one you may open, by its id; a computation by the name a [comp:…] cites — a runner's job, or a page's saved cell 'wl:477/…/2'; a Lean declaration by its full name, and with 'repo' bound to where code search finds it in that repository of the project (find_lean_declaration) — only a bound declaration with a clean axiom audit lets the claim be 'lean'; a norm of law by the act's id on the legal shelf (list_legal_references gives it as the reference's document) — an act you may read — and the place in it, or none for the act as a whole.
labelNoThe claim's label, e.g. 'thm:d5-rank5'.
titleNoA short name, e.g. 'Rank 5 is decided'; empty to clear.
numberNoIts number in the paper, e.g. '5.8'; empty to clear.
reasonNoFor a new claim with a status: on what ground.
statusNoFor a NEW claim: its status on the project's scale — open, paper, computer, lean, refuted, retracted on 'math'; draft, agreed, practice, disputed, outdated on 'law'. Default the scale's first: open, draft.
projectNoThe project key, e.g. MATH.
newLabelNoA new label for an existing claim.
statementNoThe statement, Markdown with $…$ formulas.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / bases / description
      Previous value: -"What it rests on, as a JSON array replacing the list: [{\"kind\":\"page\",\"page\":477,\"note\":\"§3\"},{\"kind\":\"computation\",\"ref\":\"kimmy/gap/m74r5u\"},{\"kind\":\"lean\",\"ref\":\"D5.rank_five\",\"repo\":\"ispacex/d5\"},{\"kind\":\"source\",\"ref\":\"Gupta 1990, Thm 2\"}]. A page is one you may open, by its id; a computation by the name a [comp:…] cites — a runner's job, or a page's saved cell 'wl:477/…/2'; a Lean declaration by its full name, and with 'repo' bound to where code search finds it in that repository of the project (find_lean_declaration) — only a bound declaration with a clean axiom audit lets the claim be 'lean'."New value: +"What it rests on, as a JSON array replacing the list: [{\"kind\":\"page\",\"page\":477,\"note\":\"§3\"},{\"kind\":\"computation\",\"ref\":\"kimmy/gap/m74r5u\"},{\"kind\":\"lean\",\"ref\":\"D5.rank_five\",\"repo\":\"ispacex/d5\"},{\"kind\":\"source\",\"ref\":\"Gupta 1990, Thm 2\"},{\"kind\":\"legal\",\"document\":31,\"place\":\"Article 6(1)(f)\"}]. A page is one you may open, by its id; a computation by the name a [comp:…] cites — a runner's job, or a page's saved cell 'wl:477/…/2'; a Lean declaration by its full name, and with 'repo' bound to where code search finds it in that repository of the project (find_lean_declaration) — only a bound declaration with a clean axiom audit lets the claim be 'lean'; a norm of law by the act's id on the legal shelf (list_legal_references gives it as the reference's document) — an act you may read — and the place in it, or none for the act as a whole."
  2. Changed2 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"theorem, lemma, proposition, corollary, conjecture or question. A new claim is a theorem unless said."New value: +"One of the project's scale (list_claims answers its 'kinds'): theorem, lemma, proposition, corollary, conjecture or question on 'math'; position, conclusion, risk or obligation on 'law'. A new claim is the scale's first — a theorem, a position — unless said."
    • changedInput schema / properties / status / description
      Previous value: -"For a NEW claim: how far it is proved — open, paper, computer, lean, refuted, retracted. Default open."New value: +"For a NEW claim: its status on the project's scale — open, paper, computer, lean, refuted, retracted on 'math'; draft, agreed, practice, disputed, outdated on 'law'. Default the scale's first: open, draft."
  3. Changed1 schema field changed
    • changedInput schema / properties / bases / description
      Previous value: -"What it rests on, as a JSON array replacing the list: [{\"kind\":\"page\",\"page\":477,\"note\":\"§3\"},{\"kind\":\"computation\",\"ref\":\"kimmy/gap/m74r5u\"},{\"kind\":\"lean\",\"ref\":\"D5.rank_five\"},{\"kind\":\"source\",\"ref\":\"Gupta 1990, Thm 2\"}]. A page is one you may open, by its id; a computation by the name a [comp:…] cites — a runner's job, or a page's saved cell 'wl:477/…/2'."New value: +"What it rests on, as a JSON array replacing the list: [{\"kind\":\"page\",\"page\":477,\"note\":\"§3\"},{\"kind\":\"computation\",\"ref\":\"kimmy/gap/m74r5u\"},{\"kind\":\"lean\",\"ref\":\"D5.rank_five\",\"repo\":\"ispacex/d5\"},{\"kind\":\"source\",\"ref\":\"Gupta 1990, Thm 2\"}]. A page is one you may open, by its id; a computation by the name a [comp:…] cites — a runner's job, or a page's saved cell 'wl:477/…/2'; a Lean declaration by its full name, and with 'repo' bound to where code search finds it in that repository of the project (find_lean_declaration) — only a bound declaration with a clean axiom audit lets the claim be 'lean'."
  4. Added

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the destructiveHint=true annotation by explaining the actual destructive mechanism ('bases given replaces the whole list'), the patch semantics ('A field left out keeps its value'), the create-if-absent behavior, and the write-permission requirement. It also documents identity resolution (by id, or by project+label) and label uniqueness rules, which annotations cannot convey.

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-loads the core verb and the sibling exclusion, and every sentence carries information. It is dense to the point of being a single wall of parentheticals, which costs a little parseability, but there is no filler.

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 an 11-parameter upsert tool with no output schema, it covers creation, mutation, identity, formats, permissions and sibling routing. The one gap is that it never says what the call returns or what happens on a failed lookup/label clash, which matters given there is no output schema to fall back on.

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 is the baseline, but the description adds real semantics not in it: replacement-vs-merge behavior for 'bases', Markdown/$…$ formatting for 'statement', the label grammar and per-project case-insensitive uniqueness, and the rename path via 'newLabel'. It stops short of adding anything for 'id' or 'number' beyond the schema.

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 specific verb and resource ('Add a claim to a project's register, or change one') and enumerates the mutable fields. It also explicitly distinguishes itself from the nearest sibling by declaring that status is not changed here and pointing to set_claim_status.

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?

Gives an explicit exclusion plus the alternative ('An existing claim's status is NOT changed here — use set_claim_status'), states the upsert condition ('one that does not exist yet is created'), and names the access precondition ('Members of the project who may write only'). Nothing about when to reach for it is left to inference.

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