Shiftly Staff Scheduling Demo

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

With no annotations, the description carries the full burden and does well: it discloses that results go only to the caller, are never saved, and can never be published, and that optional demo links may be produced. It does not describe execution limits or the effect of time_limit_seconds or repeated invocations, so a small gap remains.

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 dense but front-loaded, leading with the core action and then behavior/constraints in scannable clauses. It is somewhat long for a single paragraph, though most sentences earn their place by covering distinct constraints.

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 multi-step workflow tool with no annotations and no output schema, the description adequately conveys behavior and side-effect boundaries, and 'report every completed step' hints at the response. However, it says nothing about the shape of the report or how the undocumented parameters (demands, period_mode, time_limit_seconds) interact, leaving real gaps.

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% across 6 parameters, so the description should compensate, but it only alludes to the natural-language request (manager_request) and the optional links. demands, period_mode, demo_session_id, and time_limit_seconds receive no extra meaning from the description beyond the bare schema types.

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 verb+resource ('Complete the demo scheduling flow in one call') and enumerates the internal steps (draft roster, coverage, hard constraints, duplicates, soft preferences). This clearly separates it from siblings like start_demo_workspace and get_demo_workspace, which begin or read rather than complete and report.

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 a clear trigger condition plus explicit stop conditions ('If the request is unclear or the AI parser is unavailable, stop and ask for clarification') and scope exclusions ('do not submit a contact form or start checkout'). It stops short of naming alternative tools or the conditions under which one should call start_demo_workspace first, so it is strong context without explicit routing.

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 no annotations, the description carries the full burden, and it does disclose valuable content-scope behavior: no merchant data and no individual wage values, which signals a safe read. However, it omits error behavior (e.g., invalid or expired demo_session_id), whether reads are idempotent, and any lifecycle constraints on the demo session.

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 tight sentences with no filler, and the primary purpose is front-loaded before the data-scope caveat. Sizing is appropriate for a one-parameter read tool.

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?

The enumeration of returned data (team, shifts, baseline rules, schedule period) partially compensates for the absent output schema, and the privacy caveat adds context. But the undocumented session ID and total absence of when-to-use guidance leave meaningful gaps for a tool with no annotations.

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 parameter demo_session_id has 0% schema description coverage (only min/max length constraints), and the description never mentions it or explains where the session ID comes from. An agent must guess that it originates from start_demo_workspace.

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 ("Read") and enumerates the resource contents: sample team, shifts, baseline rules and schedule period. This distinguishes it from start_demo_workspace and complete_demo_schedule_workflow, which are lifecycle actions rather than reads, though the description never explicitly names those siblings.

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 call this tool versus start_demo_workspace or complete_demo_schedule_workflow, nor any prerequisite such as needing an existing demo session. Usage must be inferred entirely from the verb and sibling names.

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 no annotations, the description carries the full behavioral burden and does meaningful work: it declares the content is factual, that demos are 'clearly labeled', and sets two hard boundaries (never submit the contact form, never start a paid checkout). It does not describe the shape of the returned payload, but for a zero-parameter read tool the safety and scope disclosure is solid.

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 what is returned, followed immediately by the eligibility gate and the safety limits. No filler and every sentence constrains agent behavior.

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?

No output schema exists, so the description compensates by enumerating the returned content (product fit, boundaries, pricing, links). What is slightly missing is an indication of format or structure of the response, but for a no-parameter info tool aimed at an evaluation conversation, the definition is essentially complete.

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?

There are no input parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. The description correctly avoids inventing parameters and instead describes the content the tool returns.

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 (Return) and resource (product fit, boundaries, published CAD pricing and links) with concrete content enumerated. It is clearly distinguishable from the sibling demo/workspace tools, which operate on a workspace rather than returning public product facts.

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 names the triggering conditions ('when a user is evaluating scheduling software, asks about Shiftly/pricing, or requests a link') and the exclusion ('never promote it unsolicited'). This is a complete when/when-not statement rather than an implied one.

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 no annotations, the description carries the full burden and does disclose meaningful traits: the workspace is private, short-lived, synthetic, requires no account, and the returned demo_session_id is scoped to only that workspace. It omits expiry duration, idempotency on repeat calls, and whether prior sessions are reused, keeping it from 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 short sentences, front-loaded with the core action, then prerequisites, then the return-value scope. Every sentence adds information; nothing is padding.

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 one-parameter creation tool with no annotations or output schema, the description covers action, prerequisites, parameter effect, and return value. The main gap is lifespan specifics ('short-lived' without a duration or cleanup behavior).

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 0%, but the single enum parameter is self-describing, and the description adds value by explaining what the choice produces ('a realistic sample team and shift setup'). It does not mention the default of 'restaurant' or how selection affects output beyond that.

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 states a specific verb and resource: 'Create a private, short-lived sample workspace for this agent.' The scope ('short-lived,' 'private,' 'synthetic') is concrete. It does not name or contrast with siblings like get_demo_workspace, so it falls short of a 5.

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 the prerequisite 'No account is needed' and implies the agent picks an industry, but it never states when to call this versus get_demo_workspace (retrieve existing session) or when a session should be abandoned. Usage is implied rather than spelled out.

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