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

Annotations already declare read-only, idempotent, open-world, and non-destructive behavior, so the description does not need to repeat safety details. It adds useful context about what the plan returns, but does not explain prerequisites, persistence of plan_id, or rate/auth considerations.

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 a single front-loaded sentence with no wasted text. It is appropriately concise, though the terseness contributes to gaps in parameter and usage guidance.

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 the description need not fully explain return values, and rich annotations cover the safety profile. However, for a three-parameter tool with incomplete schema coverage, the description still leaves key input semantics and sibling differentiation 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 low at 33%: only 'detail' has a brief description, while 'board_link' and 'include_summaries' are undocumented in both schema and description. The description does not compensate by explaining formats, required input, or the effect of include_summaries.

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 ('Plan a Jira board') and names the key outputs (forecast end, confidence, warnings, plan_id). It is clear what the tool does, though it does not explicitly distinguish itself from siblings like pb_forecast or pb_plan_summary.

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 gives no guidance on when to use this tool versus alternatives such as pb_forecast, pb_plan_summary, or pb_warnings. Usage is only implied by the tool name and output 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 readOnly, idempotent, non-destructive and openWorld, so safety is covered. The description adds one genuinely useful non-obvious trait — that Jira-sourced text is data and not instructions, a prompt-injection warning — but says nothing about pagination despite a cursor parameter, nor about cost or result size for large plans.

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, zero filler, and the substantive statement comes first. The prompt-injection warning is terse and placed after, which is the right ordering, though 'Zero-float tasks' as an opener leans on jargon before establishing the action.

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-shape explanation is not required, and annotations cover the safety profile. What remains missing is guidance on when to call it and what plan_id/include_summaries mean — material gaps for a paged, plan-scoped analysis tool on a ten-sibling surface.

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 33%: plan_id has no description and include_summaries has no description, and only cursor references "From next_cursor." The description adds zero parameter meaning — it never mentions plan_id, include_summaries, or how pagination terminates — so it fails to compensate 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?

"Zero-float tasks in order and why each starts when it does" identifies the resource (critical-path / zero-float tasks) and the two things returned (ordering plus rationale), which an agent can map to the critical path concept. But there is no verb ('list'/'return'/'explain') and no explicit differentiation from siblings like pb_flow_metrics or pb_workload that also touch scheduling. The Jira-injection sentence is unrelated to purpose and dilutes the opening.

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 statement of when to choose this over the nine siblings, no prerequisites (does a plan need to be built first with pb_build_plan?), and no exclusions. The agent must infer from the tool name alone that this is the scheduling-analysis tool rather than a summary or metrics 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, idempotentHint, non-destructive behavior, and open-world access, so the safety profile is known. The description adds little behavioral context beyond the metrics themselves, saying nothing about auth requirements, rate limits, or how the two identifier modes behave differently.

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 a single compact sentence with no wasted words, and the metric list is front-loaded. Its terseness becomes under-specification rather than conciseness in the parameter portion, but the structure itself 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?

An output schema exists, so return-value details need not be in the description, and annotations cover safety behavior. However, with three parameters and no schema descriptions, the description leaves key input semantics and usage distinctions incomplete.

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 parameter meaning. It mentions plan_id and board_link but does not explain their formats, whether they are mutually exclusive, which takes precedence, or what happens when both are omitted; window_days is not mentioned at all.

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 the specific metrics returned — throughput, cycle time P50/P85, and aging work — so an agent can identify the tool's purpose. It is not a generic restatement of the name, though it does not explicitly contrast itself with siblings like pb_critical_path or pb_workload.

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 use when flow metrics are needed and notes that the caller should supply either plan_id or board_link. It does not explain when to choose this over sibling tools such as pb_critical_path, pb_workload, or pb_forecast, nor does it state 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 readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds the useful fact that the result is percentile completion estimates rather than a single date, but says nothing about how percentiles are computed, how fresh the data is, or what happens when scope_id is omitted.

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?

Extremely short and front-loaded, but it is a bare noun phrase with no verb, and the terse wording forces the reader to decode 'P50/P85/P95 completion' and reconcile 'fix version' with the schema. Brevity here costs clarity rather than buying it.

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 3 parameters at 0% schema coverage and a scope/scope_id dependency to convey, the description omits the essential calling contract. The existing output schema and annotations relieve it of return-value and safety duties, but the input semantics gap remains significant.

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 description only loosely echoes the scope enum (saying 'fix version' where the enum says 'milestone'). It never explains what plan_id identifies or that scope_id must be a board/milestone/epic id matching scope, so the most error-prone parameters are undocumented everywhere.

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 the concrete output (P50/P85/P95 completion estimates) and the scopes it covers, which is specific enough to separate it from pb_plan_summary or pb_critical_path. It stops short of saying whether the percentiles are dates or effort, and 'fix version' conflicts with the schema's 'milestone' enum value.

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?

No guidance on when to pick this over siblings like pb_plan_summary, pb_critical_path, or pb_flow_metrics, and no prerequisites (e.g., that plan_id must reference an existing plan). The agent must infer selection criteria from tool names alone.

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, destructiveHint=false and openWorldHint=true, so the safety profile is fully covered by structured data. The description adds nothing beyond that: no note on whether results are cached, whether 'configured' implies credentials are required, or how many sites are typically returned. The one added constraint (board links must be on one site) is unexplained.

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 clauses with no padding, so length is fine, but both are sentence fragments and the second is cryptic rather than front-loaded explanation. Brevity here comes at the cost of specification, not from eliminating waste.

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 there are no parameters to document. However, the description leaves the agent unable to judge where this fits in a plan-building workflow among nine siblings, and 'site' versus 'board' is never defined.

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 there is nothing for the description to disambiguate; the baseline of 4 applies. The description does not need to explain argument syntax or defaults.

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 fragment 'Configured Jira sites' identifies the resource (Jira sites that are configured) and aligns with the tool name, but supplies no verb and never states that it enumerates them. The trailing clause 'board links must be on one' hints at the resource relationship without clarifying what the tool actually returns.

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 explicit statement of when to call this versus the nine sibling tools (pb_build_plan, pb_workload, etc.). The 'board links must be on one' clause weakly implies it is a prerequisite step before board-scoped operations, but the agent must infer both the condition and the ordering.

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 establish that this is a read-only, idempotent, open-world, non-destructive operation. The description adds a useful safety signal that Jira text is data rather than instructions, but it does not otherwise deepen behavioral context such as pagination or data freshness.

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 compact and front-loads the milestone metrics, with the security note kept separate. It uses little space, though its brevity contributes to gaps in selection guidance and parameter meaning.

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 crowded sibling set, an agent needs clearer when-to-use guidance than this provides, especially versus pb_forecast. Output schema and annotations help with return format and safety, but the description still leaves key selection and parameter context incomplete.

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 50%, and the description does not explain either plan_id or cursor. The cursor schema note 'From next_cursor.' is minimal, and plan_id is left entirely unexplained in both description and 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 names a specific resource, milestones, and the key metrics returned: forecast vs. target and slip in working days. It lacks an explicit verb and does not differentiate itself from nearby tools such as pb_forecast or pb_critical_path, but the resource+data scope is understandable.

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 guidance on when to use this tool versus alternatives like pb_forecast, pb_critical_path, or pb_plan_summary. The only secondary sentence is a security note, not usage 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/open-world, so the bar is lower — and the description adds a genuinely non-obvious behavioral fact: returned Jira text must be treated as data, not instructions, which matters for an open-world tool ingesting user content. It stops short of noting response-size cost of raising `detail`, but that is minor against the annotation coverage.

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 fragments, zero filler, with the substantive content up front. It could be tightened into a proper sentence with a verb, but 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?

An output schema exists so return values need not be spelled out, and annotations cover the safety profile. Still missing for correct selection: what `plan_id` identifies, how the detail levels differ, and why an agent would pick this over pb_forecast or pb_milestones given the overlapping content.

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%: `plan_id` carries no description anywhere, and `detail`'s only schema text is the tautology 'Response detail.' The description does not compensate — it never mentions plan_id or explains what summary/standard/full actually change in the response.

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 enumerates concrete outputs — status counts, blocked work, forecast vs. target, milestones at risk — which makes clear this is a read-only status roll-up for a plan. However it is a noun-phrase list with no verb and, critically, it does not differentiate from siblings whose names cover the same ground (pb_forecast, pb_milestones, pb_critical_path, pb_warnings).

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 statement of when to use this tool, no prerequisites, and no pointer to alternatives despite heavy topical overlap with pb_forecast and pb_milestones. The prompt-injection sentence is a safety note, not usage 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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The only added statement, "returns resource URI and summary," duplicates what the output schema already provides, and nothing is said about rendering cost, artifact persistence, or the meaning of the resource URI.

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 single sentence is front-loaded and waste-free, but for a 9-parameter tool spanning 12 report types this is under-specification rather than disciplined conciseness. There is room for one or two more sentences that would materially improve selection accuracy.

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 9 parameters, a 12-value report enum, and nine overlapping siblings, this definition is far too thin. The output schema covers return values, but selection guidance, format/platform implications, and parameter semantics are all 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 11% across 9 parameters (only `epics` is documented), so the description is expected to compensate but adds nothing. Enum values for theme, format, group_by, and report_id are partly self-explanatory, but the distinction between plan_id, report_id, and the report-specific parameters is left entirely to inference.

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?

"Render a report" is essentially an expansion of the tool name (pb_render / Pb Render) plus a note about the return shape. It gives no sense of what kinds of reports are rendered (the 12-value report_id enum carries that) and never distinguishes this tool from siblings like pb_critical_path, pb_workload, or pb_milestones that produce overlapping artifacts.

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 prerequisites, and no mention of alternatives despite nine sibling tools with heavy conceptual overlap. An agent cannot tell from the description whether to call pb_render with report_id='critical_path' or call pb_critical_path directly.

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, openWorldHint and destructiveHint=false, so the safety profile is fully covered. The description's only extra contribution is that results include per-rule counts; it says nothing about pagination behavior despite a cursor parameter, result ordering, or volume characteristics.

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 clause with no filler, which satisfies front-loading, but the brevity reads as under-specification rather than discipline — the filter hint is the only substantive content in the whole definition.

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 shape need not be explained, but for a four-parameter tool with a required plan_id and cursor-based pagination the description leaves the agent guessing about what plan_id scopes, whether counts are aggregated across the plan or per rule, and how to page. It is too thin for the tool's complexity.

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%, and the description does explicitly indicate that filtering happens by level or by rule, mapping to the level and rule_ids properties. It adds nothing for plan_id, which is required and undocumented in both the schema and the description.

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 phrase 'Warnings and counts per rule' identifies a specific resource and signals that aggregated counts are returned alongside warnings, which is meaningful. However, there is no verb (list? get? aggregate?) and nothing distinguishes it from siblings like pb_critical_path or pb_plan_summary, which plausibly surface related plan diagnostics.

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?

'filter by level or rule' describes capability, not when to reach for this tool. There is no mention of when this is preferable to pb_plan_summary or the other diagnostic siblings, and no prerequisites or exclusions are stated.

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, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds nothing beyond that — no mention of whether weeks defaults to a full horizon, how pagination behaves, or that results are computed against the named plan; it is consistent with but silent beyond 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?

It is a single non-bloated phrase, so nothing is wasted, but the terseness is under-specification rather than economy — there is no front-loaded statement of what the tool does or returns.

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 shape need not be described. However, with four parameters at 25% description coverage, a required plan_id, a paginated cursor, and an ambiguous weeks window, the description leaves real gaps an agent must guess at before a correct call.

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 25% — only cursor is documented ('From next_cursor.'). plan_id is required yet unexplained in both schema and description (presumably a plan from pb_build_plan), account_id is undocumented, and weeks is only obliquely implied by 'per person-week' with no statement of default horizon or allowed range.

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 fragment 'Hours allocated vs. available per person-week' describes the metric the tool reports, so an agent can guess it is a workload/capacity read. But it names no verb (compute? list? aggregate?) and does not distinguish it from siblings such as pb_forecast or pb_flow_metrics, which plausibly overlap in scope.

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 at all: no indication of what question this answers versus pb_forecast or pb_plan_summary, and no prerequisites such as needing a plan_id from pb_build_plan. The agent must infer placement among nine siblings purely from the metric name.

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