Skip to main content
Glama

retry-admissibility

Decide whether a failed HTTP call may be retried, must be reconciled, or must not be repeated — Given a request's method, how it ended (response status, timeout, reset, refused), idempotency-key evidence and optional caller policy, returns retry / do-not-retry / reconcile / unknown for an agent deciding what to do after a failed tool or API call. Encodes RFC 9110 method idempotency, the proxy and retry-of-a-retry rules and Retry-After parsing; a timeout or reset is never read as success or a

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": {
      "method": "<method>",
      "ended": "<ended>"
    },
    "name": "retry-admissibility"
  }
}

Input Schema

NameRequiredDescriptionDefault
asOfNoRFC 3339 instant; needed only to turn a Retry-After HTTP-date into seconds.
actorNo
endedYesHow the attempt ended.
methodYesHTTP method, case-sensitive (GET, POST, ...).
policyNo
statusNoRequired when ended is 'response'.
attemptNo1-based number of the attempt that just ended. Default 1.
automaticNoTrue when the retry would be issued automatically (library or proxy) rather than by a deliberate decision.
retryAfterNoRetry-After header value.
requestSentNoWhether request bytes reached the network. connection-refused and dns-failure imply not-sent.
idempotencyKeyNoCaller-asserted evidence: the engine knows no vendor's key semantics.
previousAttemptWasAutomaticRetryNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does so reasonably: it names the encoded rule sets (RFC 9110 method idempotency, proxy and retry-of-a-retry rules, Retry-After parsing) and states a safety property up front — a timeout or reset is never read as success. It stops short of saying the tool is a pure/side-effect-free advisory function or of defining what triggers 'reconcile'.

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

Conciseness3/5

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

The lead clause is well front-loaded, but the body is a single sprawling run-on sentence attached by an em dash, and it terminates mid-phrase ('a timeout or reset is never read as success or a') — a truncated fragment that signals lost content and hurts readability.

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

Completeness3/5

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

For a 12-parameter tool with nested objects, no annotations and no output schema, the description does well to publish the return enum, which substitutes for an output schema. However, the one clause that would have explained the most consequential ambiguity — the boundary between timeout/reset and success — is cut off, and the criteria separating 'reconcile' from 'do-not-retry' are never given.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75%, so the baseline is 3. The description groups the inputs into decision factors (method, termination kind, idempotency-key evidence, optional caller policy) but adds no per-parameter meaning — notably it says nothing about 'actor', 'attempt', 'automatic', or 'requestSent' beyond what the schema already documents.

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 a specific verb+resource ('Decide whether a failed HTTP call may be retried') and enumerates the three outcome classes plus the four return values (retry / do-not-retry / reconcile / unknown). An agent can tell instantly this is an HTTP-retry decision engine, distinct from anything in the unrelated sibling 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?

Explicitly scopes the trigger: 'for an agent deciding what to do after a failed tool or API call', and names the inputs that qualify a decision (method, how it ended, idempotency-key evidence, caller policy). It does not name any alternative or exclusion, but no plausible sibling overlaps this domain.

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