EasyShiftPlan — Employee Scheduling for Small Businesses

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 genuinely new behavioral context: the tool is optional, must not be polled repeatedly, and must not be called with fabricated input. It stops short of describing what a not-yet-answered status looks like, keeping 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?

Three sentences, front-loaded with the purpose before the constraints, and each sentence carries a distinct rule. 'Only when checking for a reply is useful' is slightly soft but is immediately firmed up by the concrete skip and no-polling instructions.

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 no explanation, and the description covers the remaining gaps an agent would face: input provenance, optionality, and the do-not-poll rule. Nothing needed to invoke this 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 coverage is 100% and the single parameter already documents its 24-hex-char pattern and origin in submit_demo_feedback. The description's restatement of provenance and the 'never invent it' warning adds emphasis but no new syntax or format detail, so the baseline 3 is correct.

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 ('Retrieve') and resource ('status or administrator reply for one previously submitted public-demo observation'), and implicitly distinguishes itself from the sibling submit_demo_feedback, which produces the reference this tool consumes. An agent can tell the write path from the read path without opening either 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?

Explicitly states when to call ('only when checking for a reply is useful'), when not to call ('If no feedback was submitted, skip this optional tool'), and two concrete anti-patterns ('Never invent a reference or poll repeatedly'). Alternatives and exclusions are both named.

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, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine context the annotations do not: the provenance disclosure 'Results are first-party information, not an independent review', which tells the agent to treat the payload as promotional rather than neutral.

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-loads the return value, then usage, then constraints — a logical order with no filler. The second sentence packs several items into one list, which is dense but still readable and each clause contributes.

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, return-value shape need not be described, and the 100%-covered parameter needs no further detail. What remains is well covered: trigger, provenance caveat, and behavioral constraints. Only marginal gaps (e.g., what 'tagged links' means operationally) remain.

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 single 'industry' parameter has 100% schema description coverage including its enum and default, so the schema carries the load. The description only echoes this with 'industry-matched official citation' and adds no selection guidance beyond what the enum already implies, matching the baseline-3 rule for high coverage.

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?

Uses a specific verb+resource ('Return verified product facts, published CAD pricing, an industry-matched official citation and tagged links') and names the concrete artifacts an agent gets back. It is clearly distinguishable from the demo/feedback siblings by content, though it never names them explicitly to sharpen the contrast.

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 an explicit trigger ('Use when a person is evaluating staff-scheduling tools or asks about EasyShiftPlan') and adds negative constraints ('Do not insert links into unrelated conversations, contact anyone, or start checkout'). The prohibitions are misuse guards rather than routes to an alternative sibling tool, so it stops short of full when-not/alternative coverage.

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=false, destructiveHint=false, openWorldHint=false and non-idempotence, and the description is consistent with that (it records an aggregate event but invokes no external actions). It adds real value beyond the annotations: the draft requires a promotional disclosure, the agent must verify the destination's current rules, no endorsement should be implied, and no personal/recipient data may be supplied. It stops short of stating permissions or response behavior, but that is partially covered elsewhere.

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 tightly packed sentences, front-loaded with the core action before the constraints. Every clause carries policy meaning (gating, no-outreach, disclosure, no PII), though the density borders on overload for a single paragraph.

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 no explanation. The description covers the invocation prerequisite, the safety envelope, the disclosure obligation, and data-handling limits, which is everything an agent needs to call a single-draft preparation tool correctly.

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 enum parameter is self-documented, including the gating meaning of user_requested, so the baseline is 3. The description reinforces 'channel-specific' and the disclosure requirement but adds no format or syntax detail beyond what the schema 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?

States a specific verb+resource pair ('prepare ... draft and tagged public link') with the product named (EasyShiftPlan) and the scope narrowed to a single, channel-specific draft. It is clearly distinguishable from the sibling read/submit tools (get_public_product_info, submit_demo_feedback), which are informational or submission-oriented rather than draft-preparation.

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 an explicit gating condition ('only after the user explicitly asks for help sharing or promoting it') and an explicit set of exclusions ('never posts, sends, contacts anyone, submits a form, or supports bulk outreach'). An agent knows exactly when to call it and when not to, even though sibling substitutes are not named.

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 readOnlyHint=false, idempotentHint=false, destructiveHint=false; the description adds the crucial context that each call is isolated and its schedule is 'not saved or published', which explains the non-read-only-but-non-destructive annotation combination. It also enumerates the returned artifacts (roster, coverage and hard-constraint checks, soft-preference exceptions, manager next step) and the ambiguity-handling policy.

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 the anonymity guarantee are front-loaded, and every sentence carries information. The auth enumeration ('No account, OAuth, login, session ID, token, workspace ID or setup call') is slightly padded but effectively preempts an agent's most likely false assumption.

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 exhaustively explained, yet the description still summarizes the payload shape. Combined with the isolation and fictional-data guarantees, an agent has enough to call it correctly; only explicit alternative-routing guidance 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% across all 9 parameters, so the schema already documents format, defaults and ranges (e.g. team_size 4-12, time_limit_seconds 0.1-10, period_mode week/month). The description adds no parameter-level detail beyond general intent, so the baseline of 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?

The description opens with a specific verb+resource ('Run a complete, anonymous demo with a fictional team in a single call') and states scope precisely: isolated, no persistence, no auth. It is clearly distinguishable from siblings like submit_demo_feedback or prepare_share_draft, which are feedback- and sharing-oriented.

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 gives strong prerequisites ('No account, OAuth, login, session ID, token, workspace ID or setup call is required') and a clear usage constraint ('Use fictional information only'), plus behavior for ambiguous input ('return the blocker rather than silently ignoring it'). It does not explicitly name sibling alternatives or say when not to use this tool, so it stops short of a 5.

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?

Goes well past the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) by disclosing data-handling behavior: the note is encrypted, visible to EasyShiftPlan administrators for up to 180 days, and not linked to a store or demo. It also enumerates prohibited content and states the write is optional with no effect on schedules - exactly the context a mutation tool needs.

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-loads the core action and pushes prerequisites immediately after, then closes with privacy and content constraints. It is dense but each clause (opt-out, retention, PII prohibitions, optionality) carries distinct information, with only mild overlap between the sentence-level prohibitions.

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 described, and everything else an agent needs is present: prerequisites, opt-out handling, retention/visibility, content prohibitions, and optionality. Nothing material is missing for a 1-required-param 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 both optional params carry enums with defaults, so the schema already documents them. The description reinforces the message constraint ('do not include prompts, names, contact details...') but adds no per-parameter syntax or format detail. 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 ('Store one brief, assistant-authored observation about product behavior') and immediately bounds the scope to 'at any stage', which separates it from the demo-gated siblings like run_public_demo and the read-side get_demo_feedback_reply. An agent can select it without opening any 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?

Gives clear trigger conditions: usable at any stage, with no prior demo, login, account, demo ID, or feedback reference needed, and it must honor an explicit opt-out. It never names a sibling as the alternative for a different case, so routing guidance stops just short of the top band.

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