Find mentions whose title, summary, URL, suggested action, or matched keyword contain every word in the query. Use this to look for a specific topic, product, or phrase rather than a plain time window.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | ||
| from | No | ||
| role | No | ||
| limit | No | ||
| query | Yes | ||
| source | No | ||
| keyword | No | ||
| sentiment | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only and non-destructive, so the bar is lower. The description adds meaningful behavioral detail: it searches over specific fields and uses AND semantics ('contain every word'). This goes beyond annotations, although it omits details like ordering, pagination, or how filters interact.
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 two sentences, front-loaded with the core action and then a usage note. Every sentence adds value and there is no redundancy. It is appropriately concise for the tool's complexity.
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?
With 8 parameters, no output schema, and no parameter descriptions, the tool needs a richer description to cover defaults, filter behavior, and return format. The description only handles the main search behavior, leaving significant gaps for an agent to invoke the tool correctly, especially around the optional filters.
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%, so the description must compensate for all 8 parameters, but it only explains the query parameter semantics. It does not mention the purpose or meaning of to, from, role, limit, source, keyword, or sentiment, which are otherwise undocumented. The description adds value for the required parameter but leaves the rest completely ambiguous.
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 finds mentions matching a query across specific fields (title, summary, URL, etc.) with an explicit 'every word' semantic. It also distinguishes itself from time-based retrieval by saying 'rather than a plain time window', making its purpose specific and differentiated from siblings like get_recent_mentions.
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 a clear use case: 'look for a specific topic, product, or phrase' and contrasts it with 'a plain time window', which implies the alternative. However, it does not explicitly name sibling tools like get_recent_mentions or mention when not to use it beyond the time-window contrast, so it falls short of a full 5.
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.
