Add a custom search footprint to custom.json using {kw}, {loc}, and {country} placeholders so you can generate niche- and location-specific prospect queries.
Add your own search footprint (saved to custom.json). Use {kw} for keyword, {loc} for city/area and {country} for the country name, e.g. group "local", query '{loc} {kw} association members'.
| Name | Required | Description | Default |
|---|---|---|---|
| group | Yes | ||
| query | Yes |
Changes observed during successful MCP inspections.
v1.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose the key side effect: the footprint is written to custom.json. It says nothing about whether re-adding an existing group overwrites it, whether validation occurs, or whether the new footprint is immediately usable by sibling scan tools.
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?
Front-loaded with the action and persistence target, then the placeholder rules and an example. Two tight sentences with little waste, though the example is somewhat long relative to the payload it illustrates.
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 two-parameter write tool with no output schema and no annotations, the description covers purpose, persistence destination, and query syntax. The missing piece is the semantics of 'group' and overwrite behavior, but the essentials for a correct call are present.
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. It does well for 'query', naming the three placeholders {kw}, {loc}, {country} and showing a full example, but 'group' is never defined beyond appearing in the sample as "local" — its role as a label/bucket is left to inference.
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?
States a concrete verb and resource — adding a custom search footprint persisted to custom.json — and explains the templating it expects. It does not, however, distinguish itself from the sibling add_custom_directory, which an agent could easily confuse it with.
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?
Usage is only implied ('Add your own search footprint'), with no statement of when to prefer this over add_custom_directory or how the resulting footprint is later consumed by the scan tools. The worked example gives a sense of intended shape but not of selection criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.