Canarics

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

Annotations include idempotentHint=true and readOnlyHint=false, but the description adds valuable behavioral context: the tool is read-only in effect (returns a key) but has a timing consideration (polling is slow), the key is one-time and should be stored, and the tool implies a state change in the signup process. It also warns about the long polling duration, which is beyond annotations and enhances transparency. No contradiction exists.

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?

The description is concise and well-structured, with the core purpose first, followed by critical usage guidance (poll slowly) and the outcome (one-time key). Every sentence contributes to correct tool usage, with no redundant or filler content. It's front-loaded with the most important call-to-action.

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?

Given the tool's simplicity (one parameter, no output schema), the description is complete. It covers the trigger (start_signup), the expected latency, the condition for success (claim and trial live), and the exact next step (store and use as Bearer). The agent has all necessary context without needing additional return-value details, as the description implies the key is in the response.

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?

The schema covers 100% of parameters, with the single intentToken parameter fully described. The description adds context by tying the parameter to start_signup's output and explaining how it's used in the polling flow, which is helpful beyond the schema. The description doesn't need to explain the parameter further since schema is sufficient, but the contextual link adds value.

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 clearly states the tool's purpose: to follow up on a signup initiated by start_signup, and to retrieve a one-time API key when the signup is complete. It uses a specific verb ('follow') and identifies the resource (signup status) and the key, distinguishing it from its sibling by referencing the start_signup flow.

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 gives explicit usage context: it tells the agent to use this tool after start_signup, to poll slowly because the human step takes minutes, and to expect the key only after the link is claimed and trial is live. It clearly states when to use it (polling loop) and what to do with the result (store and use as Bearer key), which is excellent guidance without needing to exclude alternatives.

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 show readOnly=false etc., so the description carries the behavioral burden. It discloses that the action starts a provisioning flow, returns a claim URL that must be shown verbatim, requires SMS/terms on the claim link, auto-provisions a demo agent, and hands over an intentToken for later status checks.

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?

The description is long but every sentence earns its place: critical instructions are front-loaded ('ALWAYS show that URL... verbatim') and warnings are grouped at the end. No filler or tautology.

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?

There is no output schema, but the description explicitly states what is returned (claim URL and intentToken), what the agent must do with each, and what prerequisites exist. For a state-initiating tool with a sibling follow-up, this is complete enough for correct invocation.

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%, so baseline is 3. The description adds meaningful semantic guidance beyond the schema: companyName and website must be grounded in actual conversation content and never placeholder-guessed, and it clarifies that the claim URL/intentToken flow rather than the parameters themselves. That extra grounding justifies a 4.

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 verb ('Begin setting up') and resource ('Canarics signup') and defines the precise entry condition: a company that has no account yet. It also distinguishes itself from the sibling tool check_signup_status by explaining this tool initiates and that one tracks progress.

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 explicitly states when to use the tool, what to do with the returned claim URL, and when to switch to check_signup_status via the intentToken. It also gives exclusions: never guess missing companyName/website, ask first; never collect passwords or credentials in chat.

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