ia_filtersTurns a plain-language description of the companies you want into filters for search (f). It takes 18 to 20 seconds. It shares the daily limit of AI analyses with avaliar.
| Name | Required | Description | Default |
|---|---|---|---|
| texto | Yes | Plain-language description of what you are looking for. |
Changes observed during successful MCP inspections.
Input schema / properties / texto / descriptionPrevious value: -"A descrição em linguagem natural do que você procura."New value: +"Plain-language description of what you are looking for."Input schema / properties / texto / descriptionAdded value: +"A descrição em linguagem natural do que você procura."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes beyond the annotations by disclosing a specific 18-20 second runtime and that it draws on a shared daily AI-analysis quota with `avaliar`. Those are exactly the operational constraints an agent needs for scheduling and avoiding quota exhaustion. It does not state whether repeated identical inputs return identical filters, which matters given idempotentHint=false.
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?
Three short sentences, each with a distinct job: purpose, latency, quota coupling. The core function is front-loaded and nothing is padded or repeated.
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 no output schema, the description does convey what comes back (filters suitable for `search`'s `f` argument) plus timing and quota. It stops short of describing the filter format or how to pass it through, leaving a small but real gap for a conversion tool.
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?
Only one parameter (`texto`) and schema coverage is 100%, so the schema already carries the semantics; baseline 3 applies. The description's phrase 'plain-language description of the companies you want' is consistent with the schema but adds no syntax, length, or format guidance.
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 transformation: plain-language company description in, filters for `search` (`f`) out. It names the sibling tool it feeds, which lets an agent place it in the workflow. The cryptic abbreviation '(`f`)' for the target parameter slightly muddies the otherwise clear purpose.
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 implied rather than stated: an agent can infer it should call this before `search` when it has natural-language criteria. Latency (18-20s) and the shared AI quota give practical decision context, but there is no explicit when-not or alternative path (e.g. hand-building filters).
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.