Start monitoring a new keyword for this account. Takes an optional role (own_brand, competitor, or industry) and a short context string that sharpens relevance scoring. Enforces the account plan keyword limit and rejects keywords too generic to produce signal.
| Name | Required | Description | Default |
|---|---|---|---|
| role | No | ||
| context | No | ||
| keyword | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate this is a non-read-only, non-idempotent, non-destructive operation. The description adds useful behavioral context by mentioning plan limit enforcement and rejection of generic keywords, which are not conveyed by annotations.
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?
Two sentences deliver the core purpose, parameter purpose, and key constraints without redundant wording. Information is front-loaded and every clause adds value.
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 tool is a simple creation operation with 3 parameters and no output schema; the description covers functionality, parameter motivation, and constraints. It doesn't describe the response format or error details, but this is reasonably complete for the tool's complexity.
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 descriptions are absent (0% coverage), so the description compensates by explaining the purpose of 'role' and 'context', and enumerating role values. It doesn't detail keyword constraints, but the schema covers those.
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 function with a specific verb and resource: 'Start monitoring a new keyword for this account.' This distinguishes it from sibling tools like update_keyword and list_keywords by emphasizing 'new'.
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 implies its use for adding a new keyword but does not explicitly contrast it with alternatives such as update_keyword or search_mentions. It does state constraints like the plan limit and rejection of generic keywords, but lacks when-not-to-use guidance.
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 have distinct purposes, but the specialized mention getters (get_competitor_signals, get_pain_signals) overlap with get_recent_mentions since that function also supports role filters. The unique filtering criteria for signals are described, reducing ambiguity, but an agent might hesitate between these options.
Tool names mostly follow a verb_noun snake_case pattern, but there is inconsistency between list_keywords and get_recent_mentions for list-like operations. The specialized signal getters also deviate slightly from the standard pattern, though all names remain readable.
With 11 tools, the server is well-scoped for a mention monitoring service. The tool set covers keyword management, mention retrieval, search, digest, and reply drafting without unnecessary overlap or excessive granularity.
The surface provides strong coverage of the domain: keyword lifecycle (create, list, update with pause), mention retrieval (by id, recent, search, digest, signals), and a feedback loop. Minor gaps exist, such as the lack of a delete_keyword or single-keyword getter, but these are workaround-able.
