Skip to main content
Glama

github_pulls

GitHub — pull requests: diff, reviews, reviewers, merging.

A PR's THREAD comments, labels and assignments go through github_issues with the same number — this is intended on GitHub's side. What lives here is what is specific to a PR: the diff, reviews, line-by-line comments, and merging.

⚠️ A merged PR is closed: there is no merged state. To tell them apart, read merged_at (null = closed without merging), or op='merged'.

⚠️ mergeable may be null on op='get': GitHub computes it in the background on the first call. null means "not known yet" — ask again, above all do not read it as "not mergeable".

⚠️ op='merge' writes to the target branch and cannot be undone with one click. The three methods differ: merge adds a merge commit, squash squashes the branch into a single commit, rebase rewrites the commits. Passing sha protects against the race: if the head moved since the read, GitHub refuses instead of merging something else.

⚠️ A review without event stays PENDING (PENDING): nothing is published, nobody is notified, and it is only visible to its author. This is useful for preparing, and a trap when you thought you were approving. APPROVE can unblock a protected merge: it is an act of governance, not a comment.

⚠️ op='files' is capped at 3,000 files and omits big patches; op='commits' at 250. A massive PR is returned incomplete, without error.

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": "github_pulls"
  }
}

Input Schema

NameRequiredDescriptionDefault
opNothe operation, see above.search
shaNoop='merge' — the expected head (race protection).
_orgNoOrg (id) de CET APPEL. `oto_list_orgs()`.
baseNoop='search'/'create' — the target branch.
bodyNoop='review'/'submit_review' — the review text.
fullNolist ops only (search | files | commits | reviews | review_comments) — the page as GitHub sends it. Default: the index view (no API links; users, labels, milestones, repositories by name; a body by its `_length`).
headNoop='search'/'create' — the source branch.
pageNopage number.
repoNorepository name.
sortNoop='search' — created | updated | popularity | long-running.
eventNoop='review'/'submit_review' — APPROVE | REQUEST_CHANGES | COMMENT.
ownerNorepository owner.
stateNoop='search' — open | closed | all.
_groupNoÉquipe (id) de CET APPEL, sous son org parente.
fieldsNoop='create'/'update'/'review_comment' — the body.
numberNothe PR's number.
_run_idNoOBLIGATOIRE à chaque appel dès `run_start` ou `data_claim_next` : sans lui, l'écriture sur une ligne réservée est refusée. Hérité seulement si le serveur tient un run actif — n'y compte pas.
_accountNoCompte à OPÉRER parmi : `Julien` (org), `Tulina front` (org). `oto_identity(op='list')`.
_projectNoProjet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
per_pageNorows per page (1-100, default 30).
_instanceNoInstance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
review_idNoop='submit_review' — the pending review to publish.
reviewersNoop='request_review'/'remove_reviewers' — accounts.
commit_titleNoop='merge' — merge commit title.
merge_methodNoop='merge' — merge | squash | rebase.
team_reviewersNoop='request_review'/'remove_reviewers' — team slugs.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations at all, the description carries the entire burden and does it well: `op='merge'` writes to the target branch and is not one-click reversible, the three merge methods differ materially (merge commit vs squash vs rewrite), a review without `event` stays PENDING and is invisible to everyone but its author, `APPROVE` is a governance act, and `files`/`commits` silently truncate at 3,000/250. These are exactly the traps an agent would otherwise fall into on mutation and approval paths.

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 a one-line purpose, then the sibling boundary, then a block of clearly labelled hazard warnings — each warning carries a distinct, non-redundant fact and nothing is repeated. It is warning-dense at the expense of any compact op overview, and the emoji/bold formatting is heavier than needed, but no sentence is 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 a 17-op, 26-parameter, mutating tool with zero annotations and no output schema, the description covers boundaries, irreversible operations and silent truncation, while the schema per-parameter text handles op-to-parameter pairing and `full` documents the index-vs-raw return shape. Missing: auth/permission expectations for merge and review submission, and any statement of what `get`/`search` actually return, which matters given there is no output schema.

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; the description earns above that by adding meaning the schema does not. It explains the semantic difference between `merge`/`squash`/`rebase` (schema only lists the enum), the pending-vs-published consequence of omitting `event` (schema only lists the enum), and the nil semantics of `mergeable` on `op='get'`. It stops short of 5 because most of the 26 parameters — `full`, `base`, `head`, `sort`, `state`, `per_page`, reviewer arrays — get nothing beyond their schema text.

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?

Opens with an explicit verb+resource+scope line: 'GitHub — pull requests: diff, reviews, reviewers, merging.' It then draws the exact line against the most confusable sibling, stating that thread comments, labels and assignments belong to `github_issues` with the same number, and that what remains here is diff, reviews, line comments and merging. An agent can route between the two without opening either schema.

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 concrete when-to-use guidance for the ambiguous paths: use `merged_at` or `op='merged'` to distinguish merged from closed, retry rather than trust `mergeable: null`, pass `sha` to protect a merge against a moved head, and attach `event` when you intend to publish a review. The gap is the 17-value `op` enum itself — the description never enumerates or routes among search/get/create/update/files/commits/reviewers, and the schema's op description says only 'see above', which points at nothing.

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