get_competitor_detailGet a competitor company detail in a project context — domain, name, importance, top pages in the project SERPs, and top keywords they rank for.
| Name | Required | Description | Default |
|---|---|---|---|
| companyId | Yes | ||
| projectId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true consistent with 'Get', a read operation, so there is no safety contradiction. The description adds value by disclosing what the response includes (domain, importance, SERP top pages, top keywords), which goes beyond the annotation. However, it doesn't address potential costs like enriched/rank data freshness or whether the response could be empty for new competitors, leaving some behavioral gaps.
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?
A single sentence that front-loads the action and resource, then uses an em-dash to append return fields efficiently. No wasted words or repetition. Slight deduction because 'in a project context' is rather generic and contracts some meaning rather than expanding it, but overall deliberate and tight.
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 low-complexity tool (2 required ID params, no output schema, no nested objects), the description covers the essentials: what it gets, its scope, and what's in the response. Sibling ambiguity remains a gap—there are many 'get_*_detail' and list tools that overlap, and the description doesn't disambiguate. Given the minimal complexity, it's adequate but not thorough.
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 carries the full burden of parameter explanation—but it never names companyId or projectId. The phrase 'in a project context' loosely hints at projectId, and the parameter names are self-explanatory, but nothing clarifies that companyId must belong to the project, what 'top pages' or 'top keywords' mean as return semantics, or the cardinality relationship between the two IDs. For 2 undocumented params, the description should at least gesture at the parameter relationship.
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 uses a specific verb ('Get'), a clear resource ('a competitor company detail'), and a scope qualifier ('in a project context'), then lists the included fields (domain, name, importance, top pages, top keywords). This clearly communicates the tool's purpose. It stops short of a 5 because it doesn't distinguish itself from similar siblings like list_competitors or get_keyword_detail by name—though the field list makes the 'detail' nature fairly clear.
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?
There is no guidance on when to use this tool versus the many sibling tools. Nothing explains that list_competitors should be used to enumerate competitors first, or how this detail view differs from get_project, get_keyword_detail, or get_opportunity_detail. 'In a project context' reads as generic scoping language rather than a genuine usage rule.
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 a few pairs could confuse an agent: add_article_suggestion vs create_article_suggestion_with_input, and get_article_brief vs download_brief_markdown vs get_write_handoff all deal with brief content. The detailed descriptions help disambiguate, but the overlap is real.
All tool names follow a consistent verb_noun pattern in lowercase snake_case (create_project, list_opportunities, generate_article_brief, lint_draft). There is no mixing of camelCase, acronyms, or vague verbs, making the naming predictable and readable.
50 tools is excessive for an MCP server, even for a broad platform like content operations. While the scope is large, this many tools will overwhelm agents and increase latency and context cost. Most practical servers are well under 25.
The tool surface covers the full content lifecycle: project creation, research, opportunity clustering, content planning, briefs, drafting, linting, publishing, and reporting. Minor gaps exist (e.g., no delete_project, no remove_destination, no direct analytics beyond distributions), but they are workarounds or handled in the web UI.