Skip to main content
Glama
Sign In

Tulina

by ai.tulina.mcp
OverviewDiscussionsAdmin

github_search

GitHub — search: repositories, code, issues/PRs, accounts, commits.

q takes GitHub's qualifier syntax, passed as-is: repo:, org:, language:, is:issue / is:pr, state:, in:file…

⚠️ Cap of 1,000 results, whatever total_count announces. This counter is an estimate of the corpus, NOT the number of retrievable rows: beyond that, GitHub answers 422. The response therefore carries a computed troncature, which is also true when GitHub gave up the search midway (incomplete_results) — two causes invisible otherwise.

⚠️ Code search has its own rules, and they explain most of the "why doesn't it find it?" questions: only the default branch is indexed, files larger than 384 KB are not, and at least one real term is needed — repo:x alone is not enough. It does not return the file's content: read it afterwards with github_files op='read'.

⚠️ Its own, low usage limit (~30 requests/minute), an order of magnitude below the rest of the API.

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_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNothe query, GitHub syntax (required).
opNorepos | code | issues | users | commits.repos
_orgNoOrg (id) de CET APPEL. `oto_list_orgs()`.
pageNopage number.
sortNodepends on op — stars/forks/updated (repos), indexed (code), comments/created/updated (issues). Absent = by relevance.
orderNoasc | desc.
_groupNoÉquipe (id) de CET APPEL, sous son org parente.
_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')`.

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 supplied, the description carries the full behavioral burden and does so in detail: a hard 1,000-result cap that contradicts `total_count`, a 422 beyond it, a computed `troncature` field that is also true on `incomplete_results`, code-search indexing limits (default branch only, 384 KB ceiling, at least one real term required), and a ~30 req/min rate limit an order of magnitude below the rest of the API. These are exactly the failure modes an agent would otherwise hit blind.

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?

Three front-loaded warning blocks, each with a distinct topic (result cap, code-search rules, rate limit), and no filler sentences. The ⚠️ markers and inline bold add visual noise, but every paragraph carries non-obvious operational information that would be costly to omit.

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 12-parameter tool with no annotations and no output schema, the description covers the dominant risks: query syntax, per-op sorting behavior is left to the schema, truncation semantics, and rate limits. It does not explain how `page` interacts with the 1,000-row ceiling or what the response body otherwise contains, which is a modest remaining gap given the schema documents the meta-parameters at 100% coverage.

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 description coverage is 100%, so the baseline is 3. The description adds genuine meaning beyond it by documenting GitHub qualifier syntax for `q` (`repo:`, `org:`, `language:`, `is:issue`/`is:pr`, `state:`, `in:file`) and the constraint that `repo:x` alone is insufficient for code search, which the schema does not state.

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?

The opening line names a specific verb and resource ("GitHub — search") and enumerates the five searchable corpora: repositories, code, issues/PRs, accounts, commits, matching the `op` enum exactly. An agent can tell this apart from the listing siblings (github_repos, github_issues, github_pulls) because the description frames it as a query-driven search rather than a scoped list.

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 routes the agent onward for the common follow-up: "It does not return the file's content: read it afterwards with github_files op='read'." That is a real when-to-use-this-vs-sibling instruction. However, it never states when to prefer github_search over github_repos / github_issues / github_pulls for simple listing, nor which `op` to pick for a given intent beyond the enum names.

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

All Tulina toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources