SignUpSheet.page

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

Annotations already declare openWorldHint=true, idempotentHint=false, destructiveHint=false, so the description's added value is narrower: it discloses the two-link return contract (public share link vs private organizer link) and the downstream effect that the organizer can notify respondents by email. It does not say whether repeated calls create duplicate polls or how long links live, which keeps it below a 5.

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?

Four sentences, front-loaded with the action and mechanism before usage guidance and the exclusion. Slightly padded by the explanatory 'people open one link and answer...' clause, but every sentence contributes routing or behavioral information.

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 needn't document return shapes, and it still summarizes the key return (share link plus private organizer link). Annotations cover safety profile, schema covers all 7 parameters and limits, so nothing an agent needs to call correctly 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?

Schema description coverage is 100% and each parameter already carries its own constraints and examples, so the baseline is 3. The description adds no parameter-level detail beyond implying that options are dates/times and that organizer_email drives link delivery, which the schema already states.

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?

Opens with a specific verb and resource ('Creates a group scheduling poll on SignUpSheet.page') and immediately describes the mechanism (yes/maybe/no per date, best option highlighted). The final sentence explicitly distinguishes it from the sibling sign-up-flow tooling by ruling out 'sign-up slots' and date-less opinion polls.

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 both inclusion criteria with concrete examples (meeting, dinner, reunion, parent night, study session) and an explicit exclusion ('Not for sign-up slots or opinion polls without dates'), which routes the agent to create_signup_sheet or another tool. This is the when/when-not pattern rather than implied usage.

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 flag a non-readonly, open-world, non-idempotent write, and the description adds what those annotations cannot: two distinct returned links with different audiences, the organizer-email side effect, and the explicit 'does not hold or transfer money' boundary for chip_in. It does not cover quotas, editability, or what happens on repeat calls.

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?

Purpose and mechanics are front-loaded in sentence one, and the return-value statement closes the paragraph before any parameter detail. The occasion enumeration is long but it is the field the agent must fill, so it earns most of its length.

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 10-parameter nested write tool with an output schema, the description covers the flow, the money caveat, and the link semantics. Gaps are minor: it never says whether the card can be edited after creation or how the recipient receives the card if no organizer_email is supplied.

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 90%, so parameters are already well documented, including the chip_in sub-fields and currency defaults. The description adds only the high-level chip_in concept (pledge, pay organizer directly) and the audience distinction for the two links, so a baseline 3 is appropriate.

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 ('Creates an online group card ... for one person') and immediately explains the mechanics: one shared link, signers write messages, organizer delivers later by email/screen/print. The resource noun alone separates it from create_signup_sheet and create_date_poll, so an agent can route confidently.

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 long occasion list ('farewell, birthday, retirement...') plus the team/class/family framing gives concrete when-to-use context, and the chip_in sentence explains the money-collection variant. It stops short of naming alternatives or stating when to prefer create_signup_sheet instead, so it is clear but not exclusionary.

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 say it's a non-read-only, open-world, non-idempotent write. The description adds what the agent actually needs: a public live page with a share link, a separate private organizer link, waitlists for full slots, day-before reminders, and that money is pledged and paid directly to the organizer rather than held by the service.

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 purpose, then use-case recognition, then exclusions — a sensible order with no filler sentences. The middle use-case list is long (potluck, class party, volunteer shifts, carpool days, meal train, conference slots, supplies, classroom helpers), which aids recognition but reads as a run-on list that could be tightened.

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 an 11-parameter nested creation tool with an output schema, the description covers what gets created, what is returned (share link and organizer link), and the key downstream behaviors. Return-value detail is rightly left to the output schema and parameter detail to the fully described schema.

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. The description goes further by explaining the slot model — label, optional date and start/end time, capacity — and the behavioral consequence of capacity ('full slots get a waitlist and people get a reminder the day before'). It says nothing about the chip_in money-collection object, leaving that entirely to the 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?

Opens with a specific verb and resource ('Creates a live online sign-up sheet on SignUpSheet.page') and states the core mechanism: one shared link, no account needed. It explicitly rules out sibling use cases ('Not for voting on dates, group cards...'), which maps directly to create_date_poll and create_group_card.

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 concrete when-to-use list (potlucks, volunteer shifts, meal trains, conference slots) and an explicit when-not-to-use list (voting on dates, group cards, ticket sales, paid registration). The boundary against the two sibling creation tools is stated, not implied.

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 readOnly, idempotent, non-destructive and closed-world. The description adds genuinely new behavioral context — it reads only the *public* view and never returns email addresses or private details, which materially affects how an agent should present results and what it may promise the user. No error or invalid-link behavior is described, so 4.

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: what it reads, when to use it, what it deliberately does not expose. No hedging, no repetition, and the core purpose is front-loaded.

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 spell out return structures, and it still gives a useful gist (open/full slots, poll answers per option, signer counts). Combined with 100% schema coverage and full annotations, an agent has everything needed; only handling of invalid or non-public links is 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 coverage is 100% and the share_url property already documents the link format and the bare 8-character id fallback. The description's "Takes the public share link (signupsheet.page/s/…)" largely restates that, adding only the word 'public'. Baseline 3 is appropriate when 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?

States a specific verb ('Reads') and resource ('public status of a SignUpSheet.page sign-up sheet, date poll or group card'), and enumerates the three variants that map onto the create_* siblings. An agent can immediately tell this is the read counterpart to the creation tools without inspecting 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?

"Use it when the user asks how their sheet, poll or card is going" gives a clear selection trigger, and the public-share-link constraint narrows the context further. It stops short of stating when not to use it (e.g., private/owner views or non-existent links), 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.