Select one persisted blocker offer on the original request. Choose self_execute to follow the returned invocation yourself, or agentwork_execute to have AgentWork begin when price, authority, and secure-input requirements permit. Selection does not silently charge or procure anything.
| Name | Required | Description | Default |
|---|---|---|---|
| choice | Yes | ||
| offer_id | Yes | ||
| request_id | Yes | ||
| request_token | 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?
With no annotations, the description carries the burden of behavioral disclosure. It explicitly states that selection does not 'silently charge or procure anything,' which is a key safety clarification. It also explains the behavioral difference between executing the offer directly vs deferring to AgentWork.
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?
The description is three sentences long, with the primary purpose in the first sentence and no filler. Each sentence contributes distinct information: what the tool does, how the choice parameter works, and a crucial safety guarantee.
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?
For a selection tool with no output schema, the description covers the core action, the two execution modes, and the non-charging safety behavior. It does not describe return values or post-selection effects in detail, but the essential decision-making context is present.
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 description coverage is 0%, so the description must compensate for all four parameters. It only explains the 'choice' parameter semantics. The identifiers 'request_id', 'request_token', and 'offer_id' are not qualified beyond the generic phrase 'on the original request,' leaving their roles and constraints under-specified.
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 clearly states the tool's verb ('Select') and resource ('one persisted blocker offer on the original request'), making its primary purpose unambiguous. It also distinguishes this tool from siblings by focusing on the act of choosing among offers rather than resolving or reporting the blocker.
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 provides clear guidance on the two choice values ('self_execute' vs 'agentwork_execute') and when each is appropriate. It does not explicitly mention alternatives among sibling tools, but the selection context is clear enough for typical usage.
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 are separated by lifecycle stage, and the descriptions are detailed, but resolve_blocker and request_outcome_execution both accept work the agent cannot complete, making their boundary subtle. get_blocker_resolution and get_outcome_execution are also both private status readers, so some overlap exists even though descriptions help.
The set is mostly consistent with snake_case verb_noun names like search_work, select_blocker_offer, and report_blocker_outcome. buyer_capabilities is a bare noun phrase rather than a verb_noun, and submission verbs vary between resolve and request, but overall the naming remains predictable.
Ten tools is well within the well-scoped range for a workflow server. Each tool supports the blocker lifecycle, execution status, or work/service discovery, and none feels gratuitous.
The core workflow is fully represented: resolve a blocker, discover routes, select an offer, execute, read evidence, and report outcomes. There is no explicit cancel or request-history tool, and some search/discovery tools are not tied to a follow-up action, but these are minor gaps rather than dead ends.