PlanLimits

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 real value beyond that by disclosing the output verdict vocabulary, the fact that reset windows and reasons come back, and the important caveat that task size is a labeled heuristic because vendors don't publish per-task usage. It stops short of describing cost, latency, or what happens when plans are omitted/invalid.

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 first sentence front-loads the decision context and return contract, which is the right structure. The 23-id plan enumeration is bulky and could be delegated to list_plans/get_tool_plans, but it does carry genuine signal because the schema provides no enum for 'plan'.

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?

There is no output schema, and the description covers what comes back (verdict, plan, reasons, reset windows) closely enough for an agent to act on it. Combined with the read-only annotation and explicit heuristic caveat, nothing essential for calling or interpreting 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?

With only 50% schema coverage, the description compensates well: it defines the size labels (small/medium/large) with concrete examples, states the acceptable plan ids explicitly since the schema leaves 'plan' as an unconstrained string, and clarifies the 'current' parameter as the plan in use now. The 'task' parameter is left unexplained in both schema and description, which is the remaining 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?

A specific verb-and-resource statement with the decision context ('for agents deciding whether to start a task') and a concrete return contract: verdict go | wait | switch, a recommended plan, reasons and reset windows. It is clearly distinguishable from siblings like route_task and pick_plan because it frames the question as affordability rather than routing or selection.

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 opening clause gives a clear when-to-use context: an agent about to start a task with a known plan set and estimated size. However, it does not explicitly say when to use route_task or pick_plan instead, even though it notes it 'reuses the route_task logic' - that is a relationship hint, not a routing rule.

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 useful behavioral context beyond that: results are ordered newest-first and each entry carries a vendor source. It says nothing about pagination, volume caps, or default time window, so it is additive but not rich.

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 with no filler; the ordering and source clauses each carry real information. It is tight, though extremely terse for a tool with an optional filter whose default is unexplained.

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 does partly describe the return shape (dated entries, vendor source, newest first), which is appropriate. However, it omits what happens when 'since' is omitted and whether the list is bounded, leaving the agent to guess at the default scope.

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 a single parameter at 100% schema description coverage, the schema already documents 'since' with its pattern and format. The description never mentions the date filter or its default behavior, so it adds no meaning beyond the schema — baseline 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 gives a specific verb+resource ('Dated change log of AI coding plan and usage-limit changes'), which is clear and distinct in subject matter from get_tool_plans and recommend_plan. It never explicitly names or contrasts with those siblings, so it stops short of full differentiation.

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 when-to-use guidance, no exclusions, and no routing to alternatives among get_tool_plans/list_plans/recommend_plan. The only implied usage is that it returns a log; an agent must infer the trigger condition.

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 and openWorldHint, and the description adds genuinely useful behavioral context: it queries official third-party status pages, covers outages only, and explicitly excludes throttling/per-account limits. No auth or rate-limit detail, but the safety and scope profile is well covered.

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, front-loaded with the purpose before the exclusions and parameter rules. The provider enumeration is slightly crammed into a single line, but nothing is redundant or 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?

For a one-parameter, read-only tool with no output schema and annotations covering safety, the description supplies the source list, the exclusion rule, and the parameter contract. A brief hint at return shape (per-provider status objects vs. a flat incident list) is the only real 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 0% and the schema has no enum, so the description carries the full load — and does: it lists every accepted provider value, notes a tool id is also valid, and specifies that omission returns all providers. This is exactly the information the schema omits.

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 ('Live operational status and open incidents') and enumerates the exact sources it covers (Anthropic, OpenAI, Cursor, GitHub Copilot, Google, Windsurf). An agent can immediately tell this is a vendor-status reader, distinct from the plan/route 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?

Gives a clear negative scope rule ('Outages only: it does not detect throttling or per-account limits') and the default behavior ('omit for all'), which tells the agent when this tool is the wrong choice. It stops short of an explicit trigger like 'call this when a provider call fails', but no sibling competes for the same job.

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 that the lookup is scoped to a fixed, closed set of seven tools, which is consistent with and mildly reinforces the annotations, but it says nothing about response shape, errors for unknown ids, or rate 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?

Two short sentences, front-loaded with the purpose and followed by the only constraint that matters. 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?

For a single-parameter read tool with annotations covering safety, the description is adequate to invoke the tool correctly, and the enum compensation is the critical piece. However, with no output schema, the agent gets no sense of what 'plans and limits' actually returns.

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 schema declares tool_id as a bare string with no enum, so the description carries the full burden — and it does, enumerating all seven valid values. It does not state case sensitivity or format expectations, keeping it just below 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 resource ('plans and limits') and scope ('for one tool'), which implicitly contrasts with the sibling list_plans. It never names the sibling or explicitly says how it differs, so it stops 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?

The phrase 'for one tool' implies the use case (single-tool lookup vs. a broad listing), but there is no explicit when-to-use, no when-not-to-use, and none of the three siblings (get_recent_changes, list_plans, recommend_plan) is named as an alternative. Usage is only inferable from scope.

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 genuinely useful behavioral context beyond that: the complete field set returned and the sentinel convention that 'undisclosed values say "not disclosed"', which tells the agent how to interpret missing data rather than treat it as an error.

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, front-loaded with the scope ('All tracked AI coding tools ... with every plan') before the field enumeration, and the data-quality convention is placed last where it belongs. Every clause carries information; nothing is padded.

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 carries the return-value burden and does so well by naming the fields and the 'not disclosed' convention, and 'every plan' implies a complete unpaginated catalog consistent with openWorldHint=false. Minor residual gaps (exact result shape, any ordering or size limits) remain unstated.

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 zero parameters, so per the rubric the baseline is 4. There is no parameter surface for the description to clarify, and it correctly spends no words on inputs.

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 ('List all tracked AI coding tools ... with every plan') and enumerates exactly what fields come back (price, usage limits, window, models, source URL, checked date). It distinguishes itself implicitly as the full-catalog dump, though it never names the sibling get_tool_plans, which an agent would reasonably confuse it with.

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 only implied: 'All tracked ... with every plan' suggests this is the bulk-retrieval tool rather than a single-tool lookup or a recommendation. There is no explicit when-to-use, when-not-to-use, or reference to get_tool_plans/recommend_plan as alternatives, 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 cover the read-only and closed-world profile, and the description adds real value on top: it discloses the return shape (cheapest plan, reasons, up to 3 alternatives, source links) and honestly flags that the 'usage' rule is a labeled rule of thumb rather than authoritative. It stops short of noting what happens when no plan fits the budget or how fresh the pricing data is.

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?

Front-loaded with the outcome, then a compact parameter glossary; no filler sentences. The pipe-delimited value lists are dense but readable, and nothing redundant is repeated.

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 correctly explains the return payload, and all four parameters are documented. The remaining gaps are the no-fit/budget-exceeded behavior and any relationship to the sibling recommendation tools.

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 schema carries no enums, so the description is the only source of meaning — and it delivers all four: interface (terminal | ide | any), budget_usd (monthly USD), usage (light | daily | heavy), who (individual | team). That is a full compensation for the coverage 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?

The description gives a specific verb and resource ('returns the cheapest fitting plan') plus the exact output payload (reasons, up to 3 alternatives, source links), and anchors it to a known public tool. It does not, however, distinguish itself from the sibling 'recommend_plan', which sounds near-identical in purpose.

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 when-to-use guidance and no exclusions. With siblings named 'recommend_plan', 'list_plans', 'get_tool_plans' and 'route_task', the agent is left to guess which one to call; the description never mentions an alternative or a triggering condition.

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 cover the safety profile (readOnlyHint=true, openWorldHint=false), so the bar is lower. The description usefully adds the sort order ('highest price first') and that it mirrors the PlanLimits picker, but says nothing about behavior when no plan fits the budget or how many results come back.

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 with the filter, time basis, and ordering packed in without filler. The parenthetical reference to the PlanLimits picker is slightly insider jargon but adds a useful consistency cue.

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 2-parameter tool with no output schema and 0% schema description coverage, the description should at minimum explain the 'use' parameter and the empty-result case. Neither is present, so the definition is thin for a tool whose schema does no explanatory work.

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 carry the parameter burden. It clarifies budget_usd as a monthly USD figure, but the 'use' enum (individual/team/any) is never mentioned or explained, leaving half the parameters undocumented anywhere.

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 resource (plans) and scope (priced at or under a monthly USD budget), plus the sort order. It is clear what the tool returns, but it never distinguishes itself from the sibling list_plans, so an agent must guess whether this is the filtered/sorted variant or a duplicate of the plain listing.

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 when-to-use guidance and no mention of alternatives, even though list_plans and get_tool_plans are obvious candidates for the same intent. The reference to the 'PlanLimits budget picker' points at an internal UI feature rather than telling the agent when to prefer this tool.

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 meaningful behavioral context beyond annotations: it explains the returned recommendation, fallback, reset windows, rationale, weekly rotation, and source links, and it discloses that unknowns are labeled estimate or not published.

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 first sentence is front-loaded with the core behavior and return contents. The following sentences add useful qualifications and valid plan ids, though the plan-id list is long and makes the description dense; it earns its place by preventing invalid plan identifiers, but the structure could be cleaner.

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 and a read-only annotation profile, the description does a good job explaining what is returned, including rationale, fallback, reset timing, and uncertainty labeling. The main omission is sibling differentiation, which matters because the sibling set contains several competing recommendation tools.

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 only 50%, so the description must carry some of the parameter burden. It usefully enumerates all valid plan ids, which the schema only illustrates with one example, but it does not add meaning beyond the schema for the task and state values, which remain defined primarily in the input schema.

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 a specific verb and resource: given owned plans, usage, and task type, it returns a recommended plan plus fallback and reset details. It is clear what the tool does, but it does not distinguish itself from recommendation-oriented siblings like pick_plan, recommend_plan, or can_afford_task.

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 the input context (plans you own, usage states, task type), but there is no explicit when-to-use guidance, no when-not-to-use guidance, and no named alternative among the many similar sibling tools. An agent must infer that this is the routing/selection tool rather than a status or affordability tool.

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