WhatShouldMyBotDo

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, so the redundant 'Read-only' adds little. However, the 'drafts-first: the user reviews before anything is sent or posted' clause is genuine extra context about what the returned routine does, which annotations cannot express.

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 and with no filler. The second sentence ('Read-only') is largely redundant against the annotations, which is the only minor waste.

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 two-parameter read tool with no output schema, the description conveys what is returned (the routine/instructions) and the drafts-first behavior. It omits error handling for an invalid slug, but annotations carry the safety profile and the gap is minor.

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 both parameters (slug format and the ai_tool enum with default) are fully documented in the schema. The description restates the tool options already enumerated in the schema and adds no new syntax or format guidance, 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?

States a specific verb and resource — retrieving the copy-paste routine/instructions for one WhatShouldMyBotDo use case — and scopes it to the four supported AI tools. It does not explicitly name or distinguish itself from plan_first_agent or search_use_cases, though the slug-based retrieval implies it operates downstream of them.

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?

Usage is only implied: the schema notes the slug comes from search_use_cases or plan_first_agent, but the description itself gives no when-to-use guidance or exclusions. The 'drafts-first' note describes the artifact rather than when to call the tool.

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, but the description adds meaningful context beyond them: no account required, nothing is persisted, and the returned hours-saved figures are estimates rather than guarantees. It also pre-discloses the shape of the response, which matters because there is no output schema.

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 is front-loaded, then constraints, then the return shape; almost every sentence carries distinct information. It is slightly dense in a single paragraph and 'from the same 5 questions and the same ranking as the free planner' is a shade promotional, but nothing is truly 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?

With five parameters, three enums and no output schema, the description does exactly the work required: it explains the return payload (titles, fit rationale, estimated hours saved, schedule, guide links) and warns off guessing at user answers. An agent has everything needed to call and interpret it.

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 enum meanings are fully documented in the schema and the baseline is 3. The description adds real value by tying the inputs to 'the same 5 questions' and instructing the agent not to fabricate answers for them, which guards against the main failure mode for these enum parameters.

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?

Names a specific verb and resource ('Recommend the first AI agent... plus the next 3 jobs to add') and scopes it to small businesses, which clearly separates it from get_template and search_use_cases. An agent can tell what it produces without opening 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?

Gives explicit procedural guidance on invocation ('Ask the user the 5 questions first; do not guess their answers') and frames it as a read-only, no-account planning tool. It never names the sibling tools or states when one of them is the better choice, so it falls short of an explicit when/when-not routing statement.

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 the one-word 'Read-only.' is reinforcement rather than new information. The genuinely additive disclosure is the result cap ('up to 8 matches') and the exact fields returned, which no annotation or output schema conveys.

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 short sentences, front-loaded with the search scope before the return format and the chaining hint. The only marginally wasteful element is the standalone 'Read-only.' sentence, which duplicates the readOnlyHint annotation.

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 return contract and does so fully: match count cap plus the fields (slug, title, one-line summary, schedule, guide link). Combined with the get_template handoff, an agent has everything needed to call and chain this 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 single query parameter is fully documented in the schema, including the 2-100 character bound and examples. 'By plain words' restates that, adding no format or syntax detail beyond the schema, so 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 (search), a named resource (the WhatShouldMyBotDo library of AI agent use cases), a scope (small businesses) and the input modality (plain words). The closing sentence ties the output to get_template, so an agent can place it in the sibling workflow 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?

Clearly implies the search-then-fetch pattern via 'Use a slug from here with get_template,' which is concrete routing guidance. It does not say when to prefer this over plan_first_agent or state exclusions, so it stops short of a full when/when-not statement.

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