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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description need not repeat those. It adds meaningful behavioral context beyond annotations: it specifies handling of seconds and year fields, ? rules, weekday numbering as names, and explicitly states it explains why when the target cannot express a conversion. This enriches the agent's understanding of edge cases and error behavior.

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 two concise sentences with zero filler. The main action ('rewrites') and supported schedulers are front-loaded, followed by specific conversion rules and error behavior. Every word earns its place; no redundant information or repetition of schema fields.

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 moderate complexity (3 params, output schema exists), the description covers the core conversion behavior and error handling ('says why when the target cannot express it'). The output schema covers return values, so that need not be described. It omits details about the input expression's accepted format, but that is largely covered by the schema's maxLength and the implied cron syntax. Overall, it provides sufficient context for correct invocation, though it could mention auto-detection of 'from' explicitly rather than relying on the schema.

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 only 33% (only 'from' has a description: 'detected when omitted'). The description does not explain the 'expression' parameter or the 'to' parameter beyond listing allowed schedulers in the enum. It fails to compensate for the low coverage, leaving agents without guidance on how to format the expression or what the target scheduler value means semantically.

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 function: 'Rewrites a cron expression for another scheduler' and explicitly lists the six supported schedulers. It also mentions specific conversion details (seconds, year fields, ? rules, weekday numbering) that distinguish it from the sibling tools explain_cron and next_runs. The purpose is unambiguous and differentiates well from siblings.

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 implies usage for cron conversion but does not explicitly mention when to use this tool versus alternatives like explain_cron or next_runs. There are no exclusion criteria or comparative guidance, leaving the selection to inference. The distinct verb 'rewrites' helps, but explicit routing is missing.

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?

The annotations already declare the tool read-only, idempotent, and non-destructive. The description goes beyond that by disclosing concrete behavioral details: it handles up to 20 expressions, reports validity and reasons, identifies dialect, surfaces known gotchas, detects never-firing schedules, and returns the next 3 runs in UTC. This gives the agent a rich picture of what the tool will do.

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 sentence that front-loads the core action ('Explains up to 20 cron expressions in plain English') and then uses a compact colon-separated list to enumerate behaviors. Every phrase adds information, and the structure makes the tool's scope immediately scannable.

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 output schema exists and the annotations cover safety/idempotence, the description covers the essential invocation context: input limits, validation behavior, dialect handling, known edge cases, and return content. No critical behavioral aspect needed for selecting or calling the tool 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 50%: the dialect parameter is described ('detected when omitted') while expressions is not. The description adds some meaning by mentioning the 20-expression limit and that the tool checks dialect, but it does not fully compensate for the undocumented expressions parameter or explain how the dialect input relates to the output. The schema and description together are adequate but not comprehensive.

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 uses specific verbs ('explains', 'checks') tied to a clear resource ('cron expressions') and enumerates concrete outputs: validity, dialect, gotchas, never-firing schedules, and next runs. This content also distinguishes it from siblings like convert_cron and next_runs by showing it performs explanation and validation, not just conversion or run calculation.

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 clearly implies when to use the tool—whenever a cron expression needs explanation or validation—but it does not explicitly state when not to use it or name alternatives such as convert_cron or next_runs. There is no direct routing guidance, so the agent must infer the boundary from the feature list.

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, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it specifies the output includes local time, weekday, and UTC, and that runs in DST gaps or repeats are flagged. This helps the agent understand edge-case handling without contradicting 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?

The description is two sentences with no redundant phrasing. It front-loads the core purpose (next runs), then adds essential details (time zone, output format, DST handling). Every sentence earns its place, and the structure is efficient.

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 has an output schema (not shown) and annotations covering safety and idempotency, so the description does not need to enumerate return fields. It provides key contextual details: time zone default, output formatting, and DST edge cases. It does not mention error conditions or the default count, but count is already in the schema. Overall, it is complete enough for an agent to invoke 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?

The input schema describes three of five parameters (from, count, dialect), leaving timezone and expression without descriptions (60% coverage). The description clarifies the timezone parameter by stating the default is UTC and explains 'from' as 'after a given moment or now'. It does not add details for count or dialect, but the schema already covers those. The description partially compensates for the coverage gap, so it meets the baseline of 3.

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 verb 'list' (implied by 'The next runs of a cron expression') and the resource (cron expression), with details about time zone, output format (local time, weekday, UTC), and the starting point (after a given moment or now). It distinguishes this from siblings (convert_cron, explain_cron) by focusing on computing future executions rather than conversion or explanation.

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 implies when to use this tool (when you need the next execution times of a cron expression), but it does not explicitly contrast it with sibling tools or state when not to use it. There is no mention of alternatives or conditions that would route an agent to convert_cron or explain_cron. The guidance is implicit rather than explicit.

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