Disable access to a custom benchmark. Keeps only a minimal audit record; no underlying Agentery data is touched. Pass benchmark_id.
| Name | Required | Description | Default |
|---|---|---|---|
| benchmark_id | Yes | Your cb_ token |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that only a minimal audit record is kept and no underlying data is touched, providing useful behavioral context beyond the tool name.
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 concise sentences: the first states purpose, the second adds behavioral nuance and parameter instruction. No extraneous content; every sentence earns its place.
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 single-parameter tool with no output schema, the description covers purpose, side effects, and parameter. It could mention reversibility or error states, but overall it is sufficiently complete.
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 100% and the schema describes 'benchmark_id' as 'Your cb_ token'. The description merely repeats 'Pass benchmark_id', adding no additional meaning beyond the schema.
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 'disable access' and resource 'custom benchmark', clearly distinguishing it from sibling tools like create, get, and update. The purpose is immediately 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?
The description implies usage for disabling a benchmark, but does not explicitly state when to use this tool versus alternatives. No exclusion criteria or context is provided, only a simple instruction to pass the ID.
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 clearly distinct purposes, but a few pairs could cause confusion: get_provider vs get_provider_profile overlap in scope (one is a card, the other a full profile), and research_capability explicitly bundles find_niche, niche_report, price_benchmark, and search_providers, creating layered redundancy. However, the detailed descriptions clearly differentiate the entry-point tools from the lower-level ones.
The majority follow a verb_noun pattern (create_, delete_, get_, search_, suggest_, etc.), but a few tools use bare noun phrases (demand_signals, market_gaps, niche_report, price_benchmark) rather than imperative or get_ prefixes. This is a minor inconsistency that doesn't harm readability.
At 19 tools, the set is slightly above the ideal 3-15 range but each tool serves a distinct, justified function within the market-intelligence and provider-directory domain. The count feels appropriate for the breadth of features (search, research, comparison, pricing, indexes, benchmarks, and feedback).
The tool surface is very comprehensive: full CRUD for custom benchmarks, multiple discovery paths (search, research, gaps, demand signals), pricing and index tools, profile/detail tools, comparison and alternatives, plus outcome reporting. There are no obvious dead ends or missing critical operations for the stated purpose.
