Skip to main content
Glama

AI model deprecation and retirement dates, by provider

Check a claimed model retirement date against the register

verify_quote
Read-only

Is this right? Check a claim about a model id — its shutdown date, its lifecycle status, the replacement it was given — against the provider's own record instead of trusting it. Says whether the claim equals a stored value, appears only in the verbatim quote, or differs (and then what the record says instead). A model retirement date recalled from memory is exactly the kind of confident wrong answer that leaves a config pinned to something that stopped answering.

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": {
      "claimed_value": "<claimed_value>",
      "model_id": "<model_id>"
    },
    "name": "verify_quote"
  }
}

Input Schema

NameRequiredDescriptionDefault
fieldNoWhich field the claim is about, if you know it. Without it, every stored field of the record is checked.
model_idYesThe model id the claim is about, matched the same way model_status matches it. Where more than one record holds the id, narrow with `provider` or `record_id` — the check is refused rather than run against whichever came first.
providerNoOptional case-insensitive substring of the provider name, to pick which host's record the claim is checked against.
record_idNoOptional. The exact record to check against, as model_status returns it in record_id. Settles the case where one provider holds the same id twice (AWS Bedrock publishes two schedules for claude-3-haiku, one per region group).
claimed_valueYesThe value to check, exactly as claimed, e.g. "Terminated" or "2026-10-29".

Output Schema

NameRequiredDescriptionDefault
matchNo
recordNo
verdictYesmatches_record: the claim equals a stored value (match.match_type says how exactly). matches_quote: it appears in the verbatim source quote but is not a stored value. differs: the record was found and says something else — stored_values shows what. not_found: the record was not located, which says nothing about whether the claim is true.
attestationYes
quote_sourceNo
claimed_valueYes
stored_valuesNo
in_source_quoteNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, and the description adds real behavioral content on top: the three-outcome result shape and the fact that an ambiguous id causes a refusal instead of an arbitrary match. It does not describe pagination or failure modes for a missing record, but for a read-only verifier the disclosed refusal and result semantics are substantial.

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 the motivating question and the core check, then the result shape, then a one-sentence justification for why to bother. The closing sentence is persuasive framing rather than specification, but it is short and directly motivates correct invocation, so it largely earns its place.

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 two-required-parameter read-only verification tool with a full output schema and complete parameter documentation, the description covers purpose, result semantics and the refusal case. Only edge details, such as behavior when the model id is unknown entirely or how multiple differing fields are reported together, are left unstated.

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, but the description earns above baseline by naming concrete values for the un-enumerated `field` parameter (shutdown date, lifecycle status, replacement) and by framing `claimed_value` as an exactly-as-claimed string such as "Terminated" or "2026-10-29". It adds meaning the schema declares but does not exemplify.

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 (check/verify) against a specific resource (a claimed value for a model id), and enumerates exactly what it reports back: matches a stored value, appears only in the verbatim quote, or differs with the record's value given. That verification framing is functionally distinct from the lookup-oriented siblings model_status and upcoming_retirements, so an agent can route correctly without opening the 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 a clear triggering condition: a value recalled from memory should be checked rather than trusted, with the concrete failure mode (a config pinned to something that stopped answering) spelled out. It stops short of naming alternatives such as model_status for plain lookups or upcoming_retirements for forward-looking lists, so there are no explicit when-not rules.

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