Rush SR Maintenance

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds genuinely useful scoping behavior — Rush SR only, not other vehicles, not purchasing questions — which the annotations do not convey. It stops short of describing what the diagnosis output contains, but an output schema exists to cover that.

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 tight sentences, front-loaded with the use case before the exclusions. The embedded example 'such as why won't my Rush SR start' interrupts the opening sentence slightly but costs nothing in clarity or length.

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 read-only two-parameter diagnostic tool with an output schema, the description covers purpose, routing, and domain scope adequately. The only real gap is that the undocumented 'context' parameter is never addressed, though the output schema relieves it of explaining return values.

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 0%, so the description carries the burden, and it only partially compensates. The example 'why won't my Rush SR start' does hint that symptom is free-form natural language, but the 'context' parameter (maxLength 500) is never mentioned, nor is any guidance on what belongs in symptom vs context.

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 (diagnose) and resource (Rush SR symptom) and rules out the adjacent siblings by naming their domains: service intervals (maintenance_schedule) and step-by-step repair procedures (lookup_procedure). An agent can distinguish this tool from both siblings without opening a 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 when-to-use ('why won't my Rush SR start') and two explicit when-not-to-use cases that map directly onto the sibling tools, plus a vehicle-scope exclusion and a 'buying advice' exclusion. Routing is fully determined by the text.

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, destructiveHint=false, openWorldHint=false, so the safety profile is covered by structured fields and the bar for the description is lower. The description reinforces scope (Rush SR only, not buying advice) but does not add behavioral detail like return format or how procedures are matched.

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 tight sentences, front-loaded with the use case, then exclusions. Every clause earns its place and no filler is present.

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?

Output schema exists, so return values need not be described. For a single-param read-only tool, the description covers trigger, scope, and exclusions completely 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 description coverage is 0% for the single 'task' parameter, so the description must carry meaning. The example ('how do I bleed the brakes on my Rush SR') effectively demonstrates the expected natural-language task format, compensating for the undocumented parameter. It doesn't state the 200-char limit or explicit phrasing rules, so not 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?

States a specific verb+resource ('look up a Rush SR procedure') with a concrete example ('how do I bleed the brakes on my Rush SR'). Explicitly scopes to the Rush SR and routes the agent away from siblings with 'Do not use for a symptom diagnosis or a service interval lookup'.

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 when-to-use ('when you need steps for a task') and two explicit when-not-to-use rules that map directly onto the sibling tools diagnose_symptom and maintenance_schedule. Also excludes other vehicles and buying advice.

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, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: results are tagged with the interval they belong to (session, weekend, month, year, 150+ hours) and the user must pick the one matching the car's hours/sessions. It is missing nothing critical, though it doesn't state whether matches are fuzzy or exact.

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 tight sentences, front-loaded with the trigger condition, then the result semantics, then the exclusions. Every sentence carries routing or behavioral information; 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?

An output schema exists, so return values need not be explained, yet the description still usefully signals the interval-tagging of results. Combined with the read-only annotations and the strict scope boundary, an agent has everything needed to invoke this correctly.

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 0% and the single 'component' parameter is undocumented in the schema, so the description must compensate. It does: the parameter is implicitly defined as a service item (brake fluid, chain) drawn from a named vehicle's schedule. A concrete format/example list of accepted component strings would push this to 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?

States a specific verb+resource (checking a Rush SR service interval / maintenance schedule for a component) with concrete examples (brake fluid, chain). It explicitly carves itself away from its siblings diagnose_symptom and lookup_procedure, so an agent can route without opening a 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 positive trigger conditions ('when checking a service interval or maintenance schedule for a component'), explicit exclusions ('do not use for troubleshooting a symptom or a repair procedure'), and a scope limit ('Rush SR only... not other vehicles or buying advice'). Alternatives are effectively named by function even if not by tool name.

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