spike_list_servicesList a team's services — {totalServices, services:[{_id, counterId, name, desc, teams, org}], pagination}. Spike: GET /services (team-scoped).
| Name | Required | Description | Default |
|---|---|---|---|
| teamId | No | The 24-char hex team _id to scope this request to (x-team-id). Omit to use the configured default (SPIKE_TEAM_ID). List ids with spike_list_teams. |
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?
Annotations already declare readOnlyHint=true; description adds GET method, team-scoping, and response structure. No contradictions.
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?
Single sentence containing response shape, endpoint, and scoping info. No wasted words.
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?
Provides response structure and pagination in lieu of output schema. Complete for a list tool with given annotations.
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?
Description explains parameter semantics (header equivalent, default behavior, how to get values), adding value beyond 100% schema coverage.
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?
Description clearly states it lists a team's services with response shape and API endpoint. Distinguishes from sibling incident-related tools.
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?
States team-scoping and default team behavior, references spike_list_teams for IDs. Lacks explicit when-not-to-use but context is clear.
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.
Each tool targets a distinct resource and action (e.g., incidents, escalations, on-calls, services, teams) with no overlap. Incident tools are further subdivided by status and action, making misselection unlikely.
All tools follow a 'spike_verb_noun' pattern with snake_case. Verbs are consistently action-oriented (list, get, acknowledge, resolve, set), with only one longer name (spike_who_is_on_call_next) that still fits the pattern.
16 tools is well-scoped for an incident management server. It covers listing, fetching, and mutating incidents, plus supporting resources (escalations, on-calls, services, teams) without being overwhelming.
The tool surface covers the core incident lifecycle (trigger, acknowledge, resolve, priority) and provides read access to related resources. Minor gaps exist (no create/update/delete for non-incident resources), but the set is complete for typical incident response workflows.