Fleetkeep

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

Beyond the annotations (readOnly, idempotent, closed-world), the description discloses the substantive behavioral traits: a 300-vehicle cap sampled by registration order, an 'incomplete coverage with an unknown total' signal for larger fleets, and the rule that maintenance dates beyond 30 days are classified as open rather than dropped. That is exactly the truncation and completeness context an agent needs to avoid overstating fleet-wide results.

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 scope, category list and coverage caveat are front-loaded, and the closing 'Read-only' merely repeats the annotation. A few clauses are dense, but almost every sentence carries information the agent cannot get 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?

An output schema exists, so return values need not be explained. The description covers the category set, the date windows, the sampling cap and the coverage caveat, leaving only the `limit` parameter's semantics and any ordering rationale unaddressed.

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 `limit` parameter has no description, so the description carries the burden. Saying 'top 20' implies the default and cap, but it never explains that `limit` can be lowered below 20 (maximum 20, minimum 1) or what truncating it does to the ranking.

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 a specific verb and resource: it returns the top MOT, tax, insurance, service and open maintenance actions across a fleet of up to 300 non-archived vehicles. That is clearly distinguishable from get_vehicle_action_detail (per-vehicle) and search_vehicles (search), though neither sibling is named 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?

There is one explicit usage condition — 'Check coverage before making fleet-wide claims' — which tells the agent when the result is not authoritative. However, there is no guidance on when to prefer this brief over get_vehicle_action_detail or search_vehicles, and no stated exclusions.

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, so the trailing 'Read-only.' adds nothing new. The description does earn credit elsewhere: it discloses hard caps (20 actions, 20 reminders), warns the lists are truncated, and points to open_maintenance_count as the only exact total — behavioral traits an agent cannot get from the 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?

Three short sentences, front-loaded with the return contents followed by the truncation caveat and the exactness escape hatch. The final 'Read-only.' is redundant with annotations and is the one sentence that does not earn 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?

An output schema exists, so return fields needn't be enumerated, and the description correctly focuses on the non-obvious part: that the lists are partial and that open_maintenance_count is authoritative. The only gap is the lack of any statement about invalid or unauthorized vehicle_id behavior for a single-required-param 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?

There is one parameter and schema description coverage is 0%, so the description must carry the semantics. It adds the meaningful ownership constraint ('one owned vehicle'), implying the caller must have access to that vehicle_id, but says nothing about the UUID format or what happens for an unowned or invalid ID.

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 ('Return') and precise resources ('actions and the latest 20 reminder records') scoped to 'one owned vehicle', which clearly separates it from the fleet-level sibling get_fleet_action_brief. It stops short of explicitly naming that sibling, so the differentiation is inferable 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 phrase 'for one owned vehicle' implies this is the per-vehicle drill-down used after picking a vehicle via search_vehicles, but no when-to-use or when-not-to-use guidance is given and neither sibling is named. Usage is implied rather than instructed.

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, non-destructive and closed-world, so safety is covered. The description nonetheless adds a genuinely useful behavioral fact not present in the structured fields: results are capped at the requested limit and no total match count is returned, with the recommended remedy. Ordering of results and cost/latency behavior remain undisclosed.

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, front-loaded with what is returned and then the limit caveat. Minimal waste; the trailing "Read-only." merely restates the readOnlyHint annotation and could be dropped, keeping it just short of a 5.

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?

The tool is simple (two optional params) and has an output schema, so return values need not be described. However, the title advertises MOT and maintenance coverage while the description never explains how a query reaches those domains, leaving the core retrieval semantics underspecified for what is billed as a multi-domain search.

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 full burden for two parameters. It explains the limit's truncation semantics well, but says nothing about what the query string searches across (vehicle name, registration, MOT status, maintenance terms), which is the main semantic gap an agent would face.

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?

"Search owned vehicles" gives a specific verb and resource, and the description adds what is special about the result set (exact open-maintenance counts, earliest maintenance dates). It does not differentiate itself from the siblings get_fleet_action_brief and get_vehicle_action_detail, so an agent must infer that this is the list/search entry point rather than the detail or briefing view.

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 only usage directive is "Narrow the query if the limit is reached," which addresses result truncation rather than tool selection. There is no statement of when to prefer this tool over the two sibling tools or what a query string actually matches, so the usage context is only implied by the name and title.

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