leaveRelease a spot. Needs the chain slug, the email that joined, and the commitment id from join or status. Cancels any hold. Stripe test mode. Test cards only, no real money moves.
| Name | Required | Description | Default |
|---|---|---|---|
| chain | Yes | ||
| Yes | |||
| commitment_id | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the destructiveHint annotation, the description discloses concrete behavioral traits: cancels any hold, operates in Stripe test mode, accepts test cards only, and moves no real money. This is exactly the kind of side-effect and environment context an agent needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four short sentences, each earning its place: purpose, required inputs, side effect, and test-mode warning. The most important information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is complete enough to invoke correctly: it names all required inputs, the side effect, and the environment. It does not describe return values or error behavior, but no output schema exists and the core invocation context is covered.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the description compensates by explaining all three parameters: chain slug, email that joined, and commitment id from join or status. It adds provenance and meaning without repeating schema types.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with 'Release a spot', a specific verb and resource that clearly identifies the operation as leaving a chain. It also lists the required inputs and the effect (cancels a hold), distinguishing it clearly from sibling tools like join, park, and waitlist.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context: it is for releasing a spot and cancels a hold, which implies use when an existing commitment should be ended. It does not explicitly name sibling alternatives or state when not to use the tool, but the purpose and inputs are contextually sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target distinct actions, but join_chain and park_intent explicitly duplicate join and park as deprecated v1 versions, creating unnecessary ambiguity. Additionally, get_chain, status, and book_stats all provide overlapping chain-state information and could be confused.
Tool names mix single verbs (join, leave, park, waitlist), verb_noun patterns (get_chain, list_chains), and noun-like names (status, book_stats). The deprecated _intent and _chain suffixes add further inconsistency without a clear convention.
Ten tools is reasonable for the domain, but two are deprecated duplicates that should be removed, making the effective count eight. The remaining tools are well-scoped to the chain and waitlist workflow.
The core lifecycle is covered: discover chains, join, leave, check status, park an intent, and waitlist. Minor gaps exist around canceling a park or waitlist entry, but the surface supports the main agent workflows without dead ends.