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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond that: model IDs must be 'providerId/id' from a bundled catalog, rates come from a dated snapshot, and that snapshot is returned with the result. It does not discuss how caching or batch discounts are applied (e.g., whether cached tokens overlap inputTokens), leaving one behavioral gap.

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 purpose, followed by routing guidance and then the model-ID format constraint. No redundancy with the title, which merely restates the name.

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, and annotations carry the safety profile. The description covers provenance, ID format, and scope. The one residual gap is the relationship between cachedInputTokens and inputTokens, which an agent must guess.

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 14%, so the description must compensate, and it does for the highest-risk parameter: the required format for modelIds. It also signals the meaning of the caching and batch-discount inputs. The requests-per-day/month and token parameters are only implied rather than explained, so compensation is partial but meaningful.

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 output ('Estimate USD per request, day and month') plus the inputs it derives them from, so the tool's function is unambiguous. It also explicitly distinguishes itself from the domain of its sibling ai_subscription_stack_cost, which an agent could otherwise conflate with a generic AI-cost tool.

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?

It gives both a positive condition ('Use for an API workload budget') and an explicit exclusion ('not chat subscriptions'), which is exactly the routing decision that separates this tool from ai_subscription_stack_cost. The only minor omission is naming the sibling outright, but the exclusion is functionally sufficient.

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 the safety profile is covered. The description adds useful provenance (dated official sources) and the estimation method (annual billing vs twelve-charge estimates), but much of the remaining text restates return fields that the output schema already carries.

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 front-loaded sentences: the primary action and the secondary capability come first, then returns, then the scoping exclusion. No filler sentences and no repetition.

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 an output schema present, the description need not explain return shape, and rich annotations cover safety. It supplies scope, provenance, and an explicit exclusion, leaving only the empty-list edge case and the required/minItems inconsistency 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%, so the description must compensate, and it says nothing about planIds. The enum does list every valid plan ID, making the parameter largely self-documenting, but the description never clarifies the odd required-but-minItems-0 behavior (what an empty list returns).

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 action (total selected AI chat and coding subscriptions in USD) plus a secondary function (identify overlapping capabilities), and distinguishes itself from the sibling ai_api_cost by explicitly scoping out API token costs. An agent can identify the tool's job without opening the 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 a clear use case ('reviewing a subscription stack') and an explicit exclusion ('not API token costs'), which effectively routes the agent away from ai_api_cost. It does not name the alternative tool directly, so it stops just short of full 5-level routing guidance.

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 and closed-world, so the safety profile is covered. The description adds genuinely new behavior: a 366-day lookahead ceiling, strict-after semantics, and which syntax is rejected (L, W, #, named months) — useful limits not present in the structured fields.

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 dense sentences with no filler; the core action and its scope lead, supported features and rejections follow, and the negative boundary closes it out. Every clause carries an actionable constraint.

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 an output schema present, return values need no explanation, and the required-parameter contract plus input constraints are well covered. The only unaddressed area is failure behavior for invalid expressions or mismatched dialect syntax, which the agent must infer.

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 20%, so the description must carry the load, and it largely does: it maps count (1–10), after (UTC instant, strictly after), zone (IANA), and dialect (GitHub/Cloudflare/Quartz/AWS, matching the enum), and describes expression syntax and exclusions. It does not tie dialect-specific quirks to specific dialect values, leaving a small gap.

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 (Preview) plus resource (1–10 cron matches) and scopes it precisely: strictly after a UTC instant, within 366 days, in an IANA zone. The closing sentence 'does not install or run a schedule' explicitly separates it from the scheduling-oriented sibling recurring_schedule.

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 context is clear from the supported dialects and the stated boundary that it neither installs nor runs schedules, which is the key when-not condition against recurring_schedule. It stops short of an explicit 'use this tool when…' routing statement, 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.

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world. The description adds real value beyond that: it applies daylight saving changes, works in a fixed 09:00–17:00 window, and disclaims calendar access or invitation sending. The main omission is behavior when no valid slot exists.

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 zero filler; the constraints come first and the negative boundaries follow. 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?

With an output schema present, return-value explanation isn't required, and the description covers inputs, constraints, and boundaries well. The only gap is what an agent should expect when no 30-minute slot satisfies the window.

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 50% (date and zone documented, name not), but the description adds the crucial semantic that the date is interpreted in the first person's time zone, which the schema does not state. The 2–8 constraint is also reinforced, adding meaning beyond a bare schema read.

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 (Find), resource (30-minute meeting times), and hard constraints (09:00–17:00, 2–8 people, IANA zones). An agent can distinguish this from cron_next_runs or recurring_schedule purely from the description.

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?

Explicitly scopes what it is not: 'does not read calendars or send invitations', which tells the agent this is a pure computation, not a scheduling action. It also clarifies the date is local to the first person. It stops short of naming alternatives for scheduling-adjacent tasks, so it's clear context without full alternate routing.

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 the safety profile is covered; the description's "no task is executed or calendar updated" largely restates that. Where it adds real value is the non-obvious disclosure that times float in the importing calendar's local time zone, which affects DST and cross-zone correctness.

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: capability and outputs first, usage and non-effects second, the floating-time caveat last. Every sentence carries distinct information and there is no padding.

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 needn't be explained, and the read-only/idempotent behavior is already annotated. The description covers purpose, non-effects and time-zone semantics, but omits the 20-task cap and the meaning of the owner field, which an agent may need to fill in a valid request.

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?

With only 50% schema description coverage, the description partially compensates by tying the tool to weekly/biweekly/monthly frequencies and minutes-based hour estimates. It says nothing about the opaque owner enum (delegate/keep/decide), day, monthday, or time, leaving the most ambiguous parameter undocumented.

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?

Names specific verbs and outputs: estimate monthly hours, return recurrence rules plus a complete RFC 5545 calendar. The scope is concrete and unusual enough to be distinguishable. However, it never references siblings such as cron_next_runs, which is the nearest alternate schedule-generation tool, so differentiation still requires opening schemas.

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?

"Use to prepare a schedule" gives a general context, but there is no explicit when-not or named alternative, and the sibling cron_next_runs covers adjacent ground without being mentioned. Usage is implied rather than routed.

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