Game Day Weather

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

Annotations already declare readOnlyHint=true, so safety is covered, but the description adds genuinely new context: attribution requirement, the ban on model training, and the semantics of returned fields (call vs. chip vs. afterTip, roof.status as club announcement, changesSinceThursday). It still says nothing about result size or pagination.

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 purpose is front-loaded in sentence one, and every sentence does carry information. But the body is a choppy run of fragments ('Read call first, then note, then chip and hours') that leans on undefined jargon and would be easier to parse as a short structured list.

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 usefully explains the meaning of the fields an agent will receive and the week-scoping behavior, plus licensing terms. For a single-parameter read-only tool this is close to complete; only return shape and volume remain 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 100% and the only parameter's schema text already says 'Omit for the current week,' which the description merely repeats. No format or edge-case detail is added beyond the schema, so the baseline 3 applies.

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 opening sentence states the resource and filter precisely: games whose call is FLAG or WATCH. That is a specific retrieval scope an agent can act on. It does not, however, contrast itself with siblings like get_week_board or get_game, so an agent must infer which tool to reach for.

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 reading guidance ('Read call first, then note, then chip and hours') and week scoping ('omit it for the current week'), which implies how to consume the result. It never states when to use this tool instead of get_week_board or get_game, and names no 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?

With readOnlyHint=true the safety profile is already covered, and the description still adds substantial behavior: the precedence order (call, then note, then chip and hours), that chip is only a ±2h threshold check that does not replace the call, that afterTip is a note rather than a flag, and that roof.status does not change the call. It also discloses licensing terms ('free for agents... not for model training'), which is unusual and useful context.

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?

Length is reasonable and the parameter guidance is front-loaded, but the back half becomes a telegraphic dump of field semantics ('call is the weather call', 'chip is...', 'afterTip is...') with no grouping or lead-in, which makes it harder to parse than the content warrants.

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, so the description must carry return-value meaning; it explains call, chip, afterTip, roof.status and changesSinceThursday, which is good, but 'note' and 'hours' are only mentioned in passing and never defined. For a tool whose entire payload is jargon, that leaves a 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 coverage is 100%, so the baseline is 3, and the description earns above that by documenting the interaction the schema doesn't: 'A gameId selects that game's week when weekId is omitted' and 'omit weekId for the current week'. It also repeats usable examples (BUF/NE, 2026-w04-ne-buf) that reinforce the schema formats.

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 conveys that this returns a single game's weather/roof picture (call, chip, hours, roof status) and distinguishes itself implicitly from the week-level siblings like get_week_board. It never states the verb+resource plainly — 'One game' is closer to a title restatement — but the field-by-field explanation makes the tool's scope recognizable.

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 tells the agent how to identify a game (team or gameId, optional weekId) but never says when to reach for this tool instead of get_week_board, get_flags or get_report_card. There are also no exclusions or prerequisites for the call itself. Guidance is limited to parameter selection, not tool selection.

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 cover only readOnlyHint=true, so the description carries extra burden and does add real context: grades are historical, roof.status is an announcement that does not change the call, afterTip is a quiet note not a flag. These clarify the meaning of returned data (valuable with no output schema) but disclose nothing about auth, rate limits, or data scope.

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 two sentences are front-loaded and useful, but the description then crams a stream of unlabeled output-field jargon (call, chip, afterTip, roof.status, changesSinceThursday) into run-on sentences with no structure or grouping. It is neither concise nor easy to parse, and readers cannot tell these are output 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?

With no output schema, the description must explain return semantics and it makes an attempt, covering the card concept, weekId behavior, and several notable fields. But the field discussion is disorganized and incomplete (no overall shape, no indication of nesting), so an agent gets partial rather than complete coverage.

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 100% and the single parameter is already fully documented in the schema. The description restates the format and adds the omit-default behavior ('newest published card'), which only slightly differs from the schema's 'current week'. Baseline 3 applies since the schema does the heavy lifting.

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 opening sentence states the resource and its identity clearly: 'A published Sideline report card, the same cards as /report-cards.' It also names a sibling (get_game) for the live weather use case, giving partial differentiation. It stops short of a crisp verb+scope framing, and the remainder of the description drifts into output-field jargon rather than reinforcing the 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?

'Optional weekId (YYYY-wNN). Omit it for the newest published card' gives clear invocation guidance, and 'For the live weather call, use get_game' names one alternative. However, there is no guidance on when to use this card versus get_week_board or get_flags, and the bulk of the text is interpretation notes rather than selection criteria.

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 only declare readOnlyHint=true, and the description goes well beyond that: it defines how to interpret call vs chip ('chip... does not replace the call'), warns that afterTip is 'a quiet note, not a flag' and roof.status 'does not change call', and adds licensing constraints ('Free for agents and AI answers with attribution. Not for model training'). These are genuine behavioral/interpretation cues not present in 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?

Short, dense, and front-loaded: scope and the weekId default come first, then field semantics. Sentences are telegraphic and unsegmented, so the field-by-field guidance runs together without structure, but little is wasted.

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, so the description carries the burden of explaining return content, and it does so for the key fields (call, chip, note, hours, afterTip, roof.status, changesSinceThursday). Coverage of return values is meaningful though not exhaustive, which is strong for a single-optional-param read 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?

Schema description coverage is 100% and the schema already documents the weekId format (YYYY-wNN) and the omit-for-current-week behavior, so the description largely repeats structured data. It adds only the marginal clarification that the default is 'the same week as the homepage', which is the baseline-3 situation.

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+scope: the full public board for one NFL week, with the default behavior (omit weekId for the current week) made explicit. It is clear what the tool returns, but it never distinguishes itself from siblings like get_game or get_report_card, leaving the agent to infer the boundary.

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 one concrete usage rule ('Omit it for the current week') and notes a reading order ('Read call first, then note, then chip and hours'), but never says when to choose this tool over get_report_card or get_game, nor does it state any exclusions. Usage is implied rather than prescribed.

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