RealRun

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), so the description's added value is in disclosing the return shape: per-model headline scores, best-first ordering, cost tier, and the metric definition. That is genuinely useful context beyond the structured fields, though nothing is said about the sibling warnings surface or result limits.

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?

One sentence, front-loaded with the resource and scope, and every clause (ordering, cost tier, metric definition) conveys information the agent needs about the response.

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 must and largely does describe the return contents. It is complete enough to invoke and interpret results, though it leaves open whether warnings exist (get_warnings) and how scoring relates to recommend_model.

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 description coverage is 100% and the single parameter carries an enumerated task id with an inline example plus a pointer to list_tasks. The description only references 'a task' with no added syntax or semantics, so the schema does the heavy lifting and baseline 3 applies.

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 (headline scores per model for a task) plus scope and ordering ('best first', 'every model'), which implicitly separates it from recommend_model's single pick. It never names a sibling explicitly, so differentiation is inferred rather than stated.

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 no when-to-use or when-not-to-use guidance and never references the alternatives (recommend_model, get_warnings, list_tasks) that clearly overlap this territory. The agent must guess whether this or recommend_model is the right 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=true and openWorldHint=false, covering the safety profile, so the bar is lower. The description does add value beyond that by naming the warning categories (scam failures, invented data, inconsistency), which tells the agent what kind of risk signal it is retrieving, though it says nothing about return shape or volume.

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?

One sentence, no padding, and the resource and warning taxonomy come first. It is phrased as a noun fragment rather than a directive sentence, which slightly weakens front-loading of the 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?

For a single-parameter read-only tool with no output schema, the description supplies enough to know what is returned (flagged models and the reasons). It stops short of explaining result structure or how many models come back per task, but nothing critical for invocation is missing.

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 description coverage is 100% and the single 'task' parameter has an enum plus its own description and a pointer to list_tasks, so the schema carries the full burden. The description adds nothing about the task id beyond what the schema already states, which is the baseline 3 for a fully documented parameter.

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 identifies the resource returned (models RealRun flagged as not recommended or needing caution on a task) and gives examples of warning kinds, so an agent knows what it gets back. It lacks an explicit verb ('returns a list of...') and does not contrast itself with the sibling recommend_model or get_scores, so it stays a step short of a 5.

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_scores or recommend_model, and no prerequisites or sequencing guidance. The agent must infer that this is the safety-check counterpart to the scoring tools entirely on its own.

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 and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by disclosing what each listed item contains (item counts, test dates, results pages, playbook prices), which matters because there is no output schema; it does not cover ordering, pagination, or limits, so it is not a 5.

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 names the action, the resource, and the returned content with zero filler. Every clause earns its 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?

For a zero-parameter, read-only list tool with no output schema, the description supplies enough: it identifies the dataset and enumerates the fields returned. Minor gaps remain around result ordering or pagination behavior, but nothing blocks a correct call.

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 no parameters, which is the stated baseline of 4. There is nothing for the description to clarify about inputs, and it correctly does not invent any.

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 gives a specific verb ('List') and a specific resource ('the everyday tasks RealRun has tested AI models on'), plus the fields returned. It is clear what the tool does, but it never distinguishes itself from siblings like get_scores or get_warnings, so an agent gets no routing signal.

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 as a catalog/discovery call is strongly implied by 'list the everyday tasks... with item counts, test dates, results pages and playbook prices', so an agent can infer it is the entry point for browsing. There is no explicit when-to-use, when-not, or mention of the alternatives (get_scores, recommend_model), leaving routing 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 and openWorldHint=false, so the safety profile is covered. The description adds a genuine behavioral constraint (models flagged as not recommended by RealRun are excluded), but it does not describe what the recommendation looks like, how many models are returned, or whether it is ranked — a gap since there is no output schema.

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?

Two tight sentences with the core purpose front-loaded and no filler. The exclusion policy in the second sentence earns its place, though the phrasing 'RealRun flagged' is slightly opaque.

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 three params, no output schema, and only read-only annotations, the definition is adequate but incomplete: an agent cannot tell what a recommendation returns or how to act on it. The exclusion policy is a useful addition but does not close the return-value gap.

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 description coverage is 100%, so the schema already documents task, priority, and include_subscription, including enums and defaults. The description restates the priority values but adds no format, constraint, or interaction detail beyond the schema; baseline 3 applies.

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 (recommend) and resource (AI model) and names the inputs that drive the choice (task + priority). It is clearly distinct from the sibling read-only tools (get_scores, get_warnings, list_tasks), though it never explicitly contrasts itself with them.

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 by 'for a task given a priority' and the enumeration of priority values, but there is no explicit when-to-use/when-not guidance or reference to alternatives. The one stated constraint (never recommends flagged models) is a policy, not a usage rule.

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