Homeschool Tools

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

The description presents the operation as purely read-only ('Returns full detail for each offering'), but the annotations include destructiveHint=true. That directly contradicts the non-destructive compare/return behavior, and the description never resolves the conflict. This is an annotation contradiction.

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 are front-loaded with the use case, a useful example, and a parameter hint. Concise and readable, though the final sentence partly duplicates the schema description of the slugs parameter.

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 one parameter and an output schema, the description is nearly sufficient, but it fails to address the obvious conflict between readOnlyHint=true and destructiveHint=true. It also does not explicitly direct the agent to sibling tools for single-detail or search intents, which would improve completeness.

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 schema already documents the parameter with 100% coverage, including '2-3 offering slugs (preferred) or names.' The description's 'Pass slugs when known, names otherwise' repeats that guidance without adding new meaning, so the baseline score of 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?

The description opens with a clear trigger and resource: 'compare 2-3 specific homeschool curricula side by side,' with a concrete example ('Sonlight vs My Father's World'). It is easy to distinguish from a search or single-detail tool: this is explicitly a bounded, side-by-side comparison.

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 this when a user wants to compare 2-3 specific homeschool curricula' is an explicit usage condition. It does not explicitly name alternatives such as get_offering_detail or search_offerings, nor state when not to use this tool, so it falls just 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.

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

Annotations only declare read-only/idempotency traits; the description goes further by disclosing which filters are hard (subjects, grade_level) versus which influence ranking (learning_style, special_needs, parent_time, format_preference), and explains the widening behavior of worldview and the price-based logic of budget_max. This is precisely the kind of filter-semantics context an agent cannot get from annotations.

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 and trigger, then the filter semantics, then exclusions. Nearly every sentence earns its place, though the budget_max sentence is long and the parenthetical price caveats 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 8-parameter recommendation tool with an output schema (so return values need not be explained here), the description covers trigger, exclusions, hard/soft filter behavior, and special cases. Nothing an agent needs to invoke it correctly appears to be 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 already 100%, so the baseline is 3, but the description adds meaning the schema does not carry: subjects and grade_level are described as hard filters (with the no-grade-range exception), worldview is a soft-widening filter, and four parameters are explicitly labeled as ranking-only. That hard-versus-ranking distinction materially changes how an agent should populate the 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?

The description names a specific verb set ('find or get recommendations') and resource ('homeschool curriculum, educational programs, or learning materials'), and even states the database size ('350+ expert-reviewed homeschool offerings'). It does not, however, name or contrast with its siblings (search_offerings, compare_offerings, get_offering_detail), so an agent must infer the boundary.

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 an explicit trigger ('Use this when a user wants to find or get recommendations for...') and explicit exclusions ('Do not use for lesson planning, scheduling, legal compliance questions, or tutoring'). This is strong when/when-not guidance, though it never points to an alternative tool when the tool is not the right choice.

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?

The description discloses useful output contents, but the annotations are contradictory: readOnlyHint=true and destructiveHint=true are both set. The described behavior of returning review data aligns with readOnly and conflicts with destructiveHint, so an agent cannot confidently judge the tool's side effects. This is an annotation contradiction.

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 concise and front-loads the usage trigger, then summarizes the output. The final sentence about accepting slug/name is slightly redundant with the schema but not wasteful.

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 single-parameter read tool with an output schema, the description is fairly complete: it explains when to use it, what to pass, and what kind of content is returned. The main gap is the conflicting annotation, which is penalized under behavioral transparency.

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 description's statement that the parameter accepts a slug or name is essentially duplicated in the schema. The description adds no substantial new parameter semantics beyond 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?

The description clearly states the tool's verb and resource: getting more detail about a specific homeschool curriculum/program. It distinguishes itself from siblings by focusing on 'more detail' for a specific offering, though it does not explicitly name the sibling tools.

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 description gives an explicit trigger condition: 'Use this when a user asks for more detail about a specific homeschool curriculum or program.' It does not state when not to use it or explicitly contrast it with search_offerings/compare_offerings, but the intended context is clear.

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?

The annotation destructiveHint=true directly contradicts the description, which says the tool only looks up offerings and returns name, slug, and summary. The readOnlyHint=true supports the description, but the destructive hint creates a serious inconsistency that an agent cannot resolve confidently. Per the rubric, a description that contradicts annotations receives a score of 1.

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 three sentences with no filler. The main purpose is front-loaded, return values are summarized, and exclusions with alternatives are stated directly. Every sentence contributes to correct tool selection and invocation.

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 lookup tool with an output schema, the description covers purpose, return contents, and exclusions thoroughly. The only notable gap is the contradictory destructiveHint annotation, which creates avoidable confusion despite the description itself being 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 is only one parameter, query, and the schema already documents it at 100% coverage, including examples like 'Sonlight' or 'Beast Academy.' The description reinforces the intended use by framing the query as a specific offering or publisher name, but it does not add substantial semantic detail beyond 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?

The description uses a specific verb and resource: 'Look up specific homeschool offerings by name in the Homeschool Tools database.' It also gives concrete examples of when to use it, such as checking coverage or getting a slug, and clearly differentiates it from find_curriculum and other general-purpose tools.

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 description explicitly states when to use the tool ('to check whether a curriculum the user mentioned is covered, or to get its slug') and when not to use it ('Do not use this for general recommendations, lesson planning, tutoring, or non-curriculum questions'). It even names the alternative tool, find_curriculum, making the routing clear.

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