Skip to main content
Glama

DeployIt Product Expert

Ask about the code

ask_code
Read-only

Ask a question about the company's code and get an answer verified against its live source code and git history: product behavior, features, settings, limits, error messages, recent changes.

DURATION: a fresh investigation takes 20-60 seconds. Repeated questions without context are served from cache at once; the cache resets when the code changes.

IF IT TIMES OUT: the investigation keeps running. Ask the IDENTICAL question again about a minute later.

STATUS (also in structuredContent.status): verified = confirmed in the code; backend_only = exists server-side without a visible UI path; not_found = searched, it does NOT exist; unknown = could not conclude, do not relay as fact.

LIMITS: read-only. Some topics may be refused for your profile. On the free plan, 500 questions per month per company; cached answers never count.

Answers never contain code nor file paths.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "question": "<question>"
    },
    "name": "ask_code"
  }
}

Input Schema

NameRequiredDescriptionDefault
depthNoquick (default): up to about a minute. thorough: digs deeper; may be capped by the profile.
contextNoOptional context from your conversation (symptoms, what was tried…). Never cached: omit it for generic questions.
questionYesThe question about the code, as specific as possible. Identical wording hits the cache: after a timeout, repeat it verbatim.
repositoryNoRestrict to one repository of your access ("owner/repo" or its short name).

Output Schema

NameRequiredDescriptionDefault
answerYes
statusYes
sourcesYes
repositoriesYes
served_from_cacheYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

The annotations already cover the safety profile (readOnlyHint, destructiveHint=false, openWorldHint=false), and the description still adds substantial context they don't: 20-60 second latency, cache behavior and its invalidation, the fact that a timed-out investigation keeps running, quota limits (500/month on free, cached answers free), profile-based refusals, and a full status taxonomy with the explicit instruction not to relay `unknown` as fact. It also sets a hard expectation that answers contain no code or file paths. Nothing here contradicts the annotations; a non-idempotent read that returns cache-varying results is consistent with idempotentHint=false.

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 one-sentence purpose, then labeled sections (DURATION, IF IT TIMES OUT, STATUS, LIMITS) that make each constraint scannable. Every line carries operational information an agent needs; there is no restatement of the name or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers the full lifecycle of a call for a slow, quota-limited, read-only investigation tool: latency, caching, timeout recovery, quota, refusal conditions, and how to interpret the returned status. An output schema exists and the description correctly points to structuredContent.status rather than re-documenting the payload.

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 already 100%, so the baseline is 3, but the description adds real meaning on top: it explains that identical wording hits the cache and must be repeated verbatim after a timeout, and that `context` is never cached and should be omitted for generic questions. Depth is framed in terms of expected duration and profile capping, which goes beyond the enum's own text.

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?

States a specific verb and resource ("Ask a question about the company's code") plus the distinctive value: the answer is verified against live source code and git history. The enumerated topic scope (product behavior, features, settings, limits, error messages, recent changes) tells an agent what it can ask about. It never names or rules out the sibling tools, so the differentiation is implicit rather than explicit.

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 clear usage context: question topics, the quick versus thorough depth trade-off, and an explicit rule to omit `context` for generic questions because it bypasses the cache. It also prescribes an exact recovery procedure on timeout (repeat the identical question after about a minute). What's missing is any explicit "when not to use this" or reference to an 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