GWIX

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, not open-world), so the bar is lower; the description still adds real value by describing the return shape ('one row per dimension') and flagging that the call is free. It doesn't state size or freshness of the dimension set, but for a static reference tool that's minor.

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 second sentence ('The dimensions GWIX filters by, their ID formats and the lookup for each') largely restates the first, and 'Free.' is a dangling fragment. The lead is well front-loaded with 'Use to...', but roughly half the text is redundant.

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 burden of describing returns, and it does say one row per dimension with ID format and lookup. For a simple zero-param reference tool, an agent has enough to call it correctly, though a note on how the rows link to lookup would round it out.

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 to disambiguate and the baseline is 4. The description correctly implies a parameterless call.

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 purpose — a discovery tool that reports which filters GWIX accepts and each one's ID format and lookup. The enumerated dimension list makes the coverage concrete. It does not, however, differentiate itself from discovery-ish siblings such as lookup or crosswalk, so an agent must infer which one to consult first.

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 learn which filters GWIX accepts' gives an implied when-to-use context, and 'Free' signals no cost. There is no explicit guidance on when to call this versus lookup or describe, and no sequencing hint (e.g., call this before lookup to get the right ID format).

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 what annotations cannot: the return shape (one row per period with label, start, end, complete flag) and that the call is 'Free', which matters for an agent budgeting calls. It does not cover ordering of the returned rows or how 'complete' is determined for the current period.

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 earn their place. The third sentence is a broken fragment — 'Period labels and exact dates (weeks, 4-week months...) and the last complete week' — that has no verb, repeats the parenthetical already given, and dangles 'the last complete week' without explaining 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 no output schema, the description carries the burden of describing the return value and does so (label, start, end, complete flag). For a 3-parameter read-only lookup, that is nearly sufficient; the unexplained 'last complete week' phrase is the only thing an agent might need clarified.

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%, so the schema already documents from, to and the type enum fully. The description adds the label formats associated with each period length (4-week month, 13-week quarter, 52-week year), but says nothing new about from/to semantics or what happens when they are omitted. 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?

States a specific verb and resource twice over: resolve a period label (2026-Q3, 2026-M10, 2026-W41) into exact start/end dates, or enumerate the periods inside a date range. The concrete label examples and the 'returns one row per period' clause make it unmistakable against siblings like get_pay, which it explicitly positions itself in front of.

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?

Says to use it 'before asking get_pay or get_postings for a period', which names the alternatives and the sequencing that selects this tool. It does not state a when-not case (e.g. what to do if you already know exact dates), so it stops short of full routing guidance.

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