Unitrader

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 needs no restating. The description adds genuine value by disclosing what the response contains — a product overview covering the AI trader's mechanics, safety rules, usage modes, and pricing — which tells the agent this is a static documentation fetch rather than live account data.

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 that leads with the entity and packs the content list into one clause. No preamble, no filler, and every item in the list corresponds to information the agent might need.

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 parameters, no output schema, and annotations covering the safety profile, the description is nearly complete — it tells the agent exactly what topics come back. The only gap is routing guidance against the three siblings, which matters here because two of them (get_started, trading_lesson) are also informational.

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?

Zero parameters, so the baseline of 4 applies. Nothing in the description suggests configuration or filtering, which correctly matches an empty schema with additionalProperties: false.

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 the resource (Unitrader) and enumerates the specific content the tool returns: what it is, how the AI trader operates on a user's own brokerage account, safety rules, usage modes, and pricing. That is concrete enough to distinguish it from ai_activity_today and trading_lesson, though it never explicitly contrasts itself with get_started, the closest informational sibling.

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?

There is no statement of when to call this versus get_started, trading_lesson, or ai_activity_today. 'The three ways to use it' refers to the product's usage modes, not the tool's invocation context, so the agent is left to infer that this is the general overview/orientation call.

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 readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral facts: a fixed 24-hour rolling window, aggregation across all accounts, and explicitly that no dimension breakdown exists — the main way an agent could misuse this tool. It stops short of describing the shape of the returned counts.

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 dense sentence that front-loads the four metrics and ends with the scope restriction, which is the most important caveat. Every clause maps to a distinct returned value; there is no filler or restatement of the title.

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 parameters and rich annotations, the description carries almost everything an agent needs. The remaining gap is the return shape: there is no output schema, and the description does not say whether the result is four named counter fields or something else, so an agent cannot predict how to read 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 tool takes zero parameters, so the baseline is 4. The description correctly implies there is nothing to configure by stressing that the window and scope are fixed, though it does not explicitly say 'takes no arguments'.

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 the exact resource (Unitrader's AI activity over the last 24 hours) and enumerates the four counts returned: market checks, wait decisions, risk-blocked ideas, and placed trades. That is far more specific than the title, and it is clearly distinct from the informational siblings (about_unitrader, get_started, trading_lesson).

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 clause 'Platform-wide counts only: no markets, accounts or people' implicitly tells the agent this tool cannot be used for per-account or per-market questions, which is useful exclusion guidance. However, it never names an alternative tool or states a positive use case ('use when the user asks how active the AI has been'), so the when-to-use routing 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.

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety and side-effect profile are covered structurally. The description adds that the payload is a sign-up link and a starting guide with free practice money, but says nothing about the return shape or whether the link requires an account.

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 short sentence with no filler, and the core value (getting-started info plus signup link) is front-loaded. The phrasing 'beginning free with practice money' is slightly awkward but not wasteful.

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 parameterless, read-only informational tool with no output schema, the description covers the essentials of what the agent gets back. However, it leaves the boundary with about_unitrader undefined, which is the one gap that could cause a mis-selection.

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 tool takes zero parameters and the schema is empty, so there is nothing for the description to disambiguate. Baseline 4 applies; a brief note that no arguments are ever needed would have made it a 5.

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 states what the tool returns: onboarding guidance plus the link to sign up, including the free practice-money angle. That is more specific than the name/title alone, though it does not explicitly contrast itself with the sibling about_unitrader, which covers overlapping ground.

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?

There is no explicit when-to-use statement, no exclusion of alternatives, and no mention of when an agent should prefer about_unitrader or trading_lesson instead. The newcomer audience is only weakly implied by 'beginning free with practice money'.

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, closed-world, so the safety profile is covered. The description adds valuable non-annotation context: output is short and plain-English, it is educational with no recommendation, and the no-argument behavior is a listing rather than a lookup.

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, front-loaded with what the tool returns, followed by the intended audience/limits and the no-parameter behavior. No filler and nothing repeated from the schema or annotations.

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 one-optional-parameter read tool with full annotation coverage and no output schema, the description covers scope, tone, and the omitted-argument case. Only minor gaps remain, such as whether a lesson is a single item or a multi-section response, which is largely implied by "short".

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 topic parameter already has examples, so baseline is 3. The description adds genuine meaning the schema lacks: omitting topic switches the tool into list mode rather than returning an error or a generic answer.

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+resource ("a short, plain-English lesson") with concrete example topics and a second scope ("how Unitrader handles it"). It implicitly separates itself from about_unitrader by being topic-level education rather than product overview, but no sibling is named.

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?

"Leave the topic out to list the lessons" gives an explicit conditional for the empty case, and "Education only, never a recommendation" sets the framing for when this is appropriate. It does not explicitly exclude the closest alternative (about_unitrader), so 4 rather than 5.

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