Skip to main content
Glama

tollbooth-sample

by io.github.lonniev

weather_delete_operator_credential

Remove a single operator secret field.

Deletes one key from the operator's encrypted credential blob without touching the others — the field-level counterpart to forget_credentials, which wipes the whole row. Use it to retire a leftover after an SDK cutover (a Prefect key after Modal, or a stored but untemplated orphan like anthropic_api_key) without taking the operator down for a full re-delivery.

Stored-but-untemplated fields are first-class: the delete is keyed on what is vaulted, not on what the current template declares. Idempotent — already-absent fields report removed: false without rewriting the vault. RESTRICTED to the operator — requires proof (nsec-signed kind-27235 or a cached dpop_token phrase); patron proofs are rejected. A deletion is as destructive as a write.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fieldYesThe operator credential field to remove (templated or not).
dpop_tokenYesOperator proof for this tool.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added

TDQS

A5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden. It discloses idempotency, the 'removed: false' behavior for absent fields, the authentication requirements (nsec-signed kind-27235 or cached dpop_token phrase), and explicitly states 'A deletion is as destructive as a write.' This is thorough and beyond what the schema provides.

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?

The description is front-loaded with a clear one-line summary, then uses compact paragraphs to convey nuances without fluff. Every sentence adds value—usage examples, idempotency, auth, and destructive nature—making it well-structured for an agent to parse.

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?

Given the tool's mutating nature, complex auth, and no annotations, the description covers all essential aspects: purpose, alternatives, parameter semantics, side effects, idempotency, and restrictions. The output schema exists, so return details are not needed in the description.

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

Parameters5/5

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

Although schema coverage is 100%, the description adds significant meaning: the `field` parameter is clarified as keyed on what is vaulted rather than template-declared, and `dpop_token` is expanded with concrete proof types. This goes well beyond the schema's terse descriptions.

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 description opens with 'Remove a single operator secret field,' a specific verb+resource statement. It explicitly distinguishes itself from the sibling tool `forget_credentials` by calling itself the 'field-level counterpart' that deletes one key without touching the whole row, making its purpose unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear usage context: 'Use it to retire a leftover after an SDK cutover...' and contrasts with `forget_credentials` which wipes the whole row. It also specifies the operator-only restriction and that stored-but-untemplated fields are handled, giving the agent concrete conditions for selection.

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

All tollbooth-sample toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.4/5.0
Disambiguation4/5

Most tools have clearly distinct purposes with detailed descriptions, and the few similar pairs (e.g., check_balance vs check_authority_balance, account_statement vs account_statement_infographic) are well-differentiated by their descriptions. However, some overlapping concepts like forget_credentials vs delete_patron_credential/delete_operator_credential could still cause misselection without careful reading.

Naming Consistency2/5

All tools share the misleading 'weather_' prefix, which does not reflect their actual domain (billing, credentials, coupons, notarization). Naming patterns are inconsistent, mixing verb_noun (check_balance, list_coupons) with noun-ish names (account_statement, current, forecast) and varied verbs (get, list, check, request, receive, update, delete, forget, mint, redeem, etc.).

Tool Count1/5

With 52 tools, this is an extremely large surface for a sample server. Even though the domain is broad, this count far exceeds the typical well-scoped MCP server and creates unnecessary complexity for agents to navigate.

Completeness4/5

The tollbooth/billing domain is well-covered: credit purchasing, coupons, credentials, proofs, pricing models, notarization, and operator/patron status. Minor gaps exist (e.g., no single-coupon getter, no direct patron list), but core workflows have no dead ends. The weather aspect is thin with only three tools, but that seems intentional as an example paid service.

Resources