Nava: UGC creators who are your customers

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint=false and openWorldHint=false; the description adds substantial behavior the agent could not otherwise know: an async job pattern returning a job_id plus instant partial matches, a graded fresh pass within ~2 minutes, the get_job wait semantics, free-plan quota of 5 creators per email, and that paid plans return a Stripe payment link before search starts. It also discloses that the full contact list is emailed, which is a real side effect not captured by annotations.

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 capability and criteria, and the async/plan details follow in a logical order. It is dense but the email-collection and payment-link passages repeat context already implied in the schema, so it is slightly longer than it needs to be.

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 12-parameter, async, plan-gated tool with no output schema, the description covers initiation, return shape (job_id + instant matches), the required follow-up call, quota limits, and payment gating. An agent has enough to invoke it correctly and to handle the post-call flow.

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 92%, so most parameters are already documented; the description still adds value by explaining the consequence of must vs nice ('Only exact fits are returned, each with the quoted evidence for every must-have') and by instructing the agent to collect contact_email and product_url together. Marginal but genuine enrichment beyond the schema text.

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?

Opens with a specific verb and resource: 'Starts a search for real TikTok creators who are the brand's customer,' then narrows with concrete criteria (bio/posts evidence, active last 30 days, 0.3x followers view floor). It also names the follow-up sibling get_job, so an agent can distinguish this initiation tool from the job-polling tool without opening either schema.

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?

Explicit routing rule: 'Use it when the brief is about who the creator is, not just a topic or follower count.' It also states prerequisites (needs the user's email; ask for email and product website in one short question) and the immediate next action ('call get_job right away'), leaving nothing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations by disclosing long-poll blocking behavior, the repeat-until-terminal-state loop, and the rich result payload (quoted evidence per must-have, follower/view metrics, contact route, funnel counts). Annotations already cover the read-only/idempotent safety profile, so this added operational context is the right kind of contribution; only failure behavior is left unstated.

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 core purpose, but the long parenthetical is bloated and contains a redundant repetition ('how many were found, and the funnel (how many were found, active and checked)'). The wait_seconds range is restated from the schema, so a few phrases do not earn their 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?

With no output schema, the description correctly takes on the burden of describing return values in detail, and it covers the async/polling lifecycle. It stops short of describing the failure state payload or behavior for an unknown/expired job_id, which matters for a job-status 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?

Schema coverage is 50%: wait_seconds is already documented in the schema, and the description largely repeats its range while adding the blocking semantics. job_id is never explicitly explained, though 'of a find_creators search' implies it is the identifier returned by that tool.

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 specific verb and resource: retrieve status and results of a find_creators search, and names the sibling find_creators that produces the job. An agent can distinguish this from find_creators (which starts a search) without opening either schema.

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?

Gives explicit polling guidance: it waits up to 45 seconds, and you should 'call it again until status is done or failed.' The implicit sequencing after find_creators is clear from the opening clause, though no exclusion is stated relative to get_request, which could also look like a retrieval tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuine value beyond that by disclosing the return contents - status enum values, Nava's latest message, and the creators who accepted - which is important since there is no output schema. Error behavior for an unknown request_id is not addressed.

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 front-loaded sentence naming the resource, then the returned data. The parenthetical status list is long but earns its place by telling the agent what values to expect.

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 simple one-parameter read tool with no output schema, the description covers the essential return shape (status, message, acceptances). Only the handling of an invalid or unknown request_id is left unstated.

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?

There is one parameter (request_id) at 0% schema description coverage, so the description carries the burden. The context implies the id identifies a request_outreach request, but the description never states the expected id format or where an agent obtains it, leaving a small gap.

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 names a specific resource and read action: the status/message/creator set for a request_outreach request, with the full status vocabulary spelled out. It implicitly distinguishes itself from the sibling request_outreach (which creates) by describing only retrieval, though it never names a sibling explicitly.

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: an agent can infer this is the follow-up call after request_outreach to poll progress. There is no explicit when-to-use/when-not-to-use guidance and no mention of alternatives such as get_job or estimate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only flag this as a non-readonly, non-idempotent write; the description adds the material behavior an agent cannot infer: a human reviews and quotes within a day, nothing reaches creators until that quote is accepted, and the call returns a request_id rather than results. That approval-gate detail is exactly the context needed before committing a mutation.

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?

Four short sentences: what it does, what to supply, what the human loop looks like, what comes back. The outcome and the no-send-until-accepted guarantee are front-loaded with no filler.

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 15-parameter mutation with no output schema, the description covers the workflow, the approval gate, and the return value (request_id), which is most of what an agent needs. It leaves open whether repeated calls create duplicate requests and how the resulting request_id is later checked, though a sibling get_request likely handles the latter.

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 80%, so most parameters already carry their own descriptions. The description restates the four required fields and the two optional seeding inputs, but adds no semantics beyond what the schema documents, which is the expected baseline when the schema does the heavy lifting.

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?

"Nava contacts creators with the brand's brief and returns who said yes, with their rates" names a specific actor, action, and output, and implicitly separates this tool from the sibling find_creators (search) by framing it as the outreach step. An agent can tell what it produces (responses plus rates) without opening the schema.

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?

It states the inputs to supply and notes that job_id comes "from find_creators" and creator_handles can seed the run, which implies the sequencing after a search. It stops short of an explicit "use this instead of X when Y" rule, so the when-not guidance is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.