VA Heroes PH — From Zero to Hero | Become a Virtual Assistant

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so safety is known. The description adds vital behavior beyond that: it describes the NOT_FOUND error for unknown slugs and states that the error lists valid slugs, plus it explicitly enumerates the return fields and their absence. No contradiction with 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?

The description is long but every sentence earns its place: it front-loads the primary purpose, then explicitly ties usage to a sibling, explains parameter behavior, lists return fields, and closes with exclusions. It is well-structured and avoids redundancy with the schema's example by adding error-handling nuance.

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-only tool with a full output schema, the description is remarkably complete. It covers what the tool returns (all key fields), what it cannot do (pricing, scheduling, application), and how it behaves on invalid input. Even though an output schema exists, the description's additional exclusions and error details ensure an agent will not misuse the 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%, so the schema already documents 'slug' with an example. The description adds extra value by explaining the consequence of an unknown slug (NOT_FOUND with valid slug list) and reinforcing that the slug must exactly match an existing path. This goes beyond the schema's static description, justifying a score above the baseline 3.

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 ('Retrieve') and a specific resource ('full published detail of one VA Heroes PH Hero Path'), and distinguishes itself from the sibling get_hero_paths by clarifying it returns a single record identified by slug. It also states exactly when to use it ('after get_hero_paths when the user asks about one track'), making the purpose unambiguous.

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 says to use it after get_hero_paths when the user asks about a single track, and it enumerates what it does NOT return (pricing, schedules, enrolment, applicant data) and that it cannot submit an application. This gives an agent clear boundaries for when this tool is appropriate versus other siblings, even if alternatives are not all 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?

The annotations already mark the operation as read-only, idempotent, and non-destructive, and the description adds meaningful behavioral context: it returns only publicly published data, excludes pricing/schedules/enrolment/private records, and cannot submit an application. These details tell the agent exactly what side effects and data boundaries exist.

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 every sentence earns its place: purpose, use case, parameter guidance, return shape, and explicit exclusions are all covered without repetition. The most important scoping information 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?

Given that an output schema exists and annotations already declare the safety profile, the description is more than sufficient. It explains when to call the tool, what it returns, what it excludes, and how it relates to get_hero_path. An agent has everything needed to select and invoke it 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?

The schema documents all three parameters, but the description enriches them: it maps 'training' to VA skill paths and 'sales' to the Loan Officer path, explains 'featured' as the recommended starting path, and gives the valid range for 'limit'. This goes beyond the raw schema definitions.

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 and resource ('Retrieve every publicly published VA Heroes PH Hero Path'), explains what Hero Paths are, and distinguishes from get_hero_path by stating it is used to obtain a slug before calling that singular-path tool. This leaves no ambiguity about the tool's purpose.

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 explicitly states when to use the tool: 'when someone asks what programs, tracks, specialisations or career options VA Heroes PH offers, or to obtain a slug before calling get_hero_path.' It also clarifies what it cannot do, which helps an agent avoid misusing it for application submission or private data.

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 mark the tool as read-only, idempotent, and non-destructive; the description adds valuable context beyond that by stating it requires no input, returning only a predefined overview shape. It also explicitly excludes pricing, class schedules, enrolment status, batch dates, and applicant data, and clarifies that no separate course catalogue exists, which prevents false expectations.

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?

Every sentence earns its place: purpose, when to use, no-input requirement, return shape, and explicit non-scope. The most important selection information is front-loaded before the negative contract, and there is no redundancy.

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 zero-input, read-only overview tool with sibling distinctions, the description covers purpose, usage, return structure, and limitations. Nothing an agent needs to decide when to call it is missing, and the output schema provides the detailed return formatting.

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 zero parameters, and the empty schema already implies no input; the description makes this explicit with 'Requires no input,' which is exactly the guidance an agent needs for a parameterless tool. The 0-parameter baseline is 4, and the explicit statement raises it to 5.

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 and resource: 'Retrieve a single structured overview of how the VA Heroes PH program works,' then enumerates exactly what that overview contains: Hero Paths, the sales/Loan Officer path, impact stats, and the application page. It also distinguishes itself from specific-track tools with 'instead of asking about one specific track.'

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 clear when-to-use context ('Use it when a visitor asks broadly what VA Heroes PH offers, how the training works, or how to get started') and an explicit when-not ('instead of asking about one specific track'). However, it does not explicitly name the alternative sibling tools, so the agent has to infer them from the sibling list.

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 readOnly, idempotent, and non-destructive behavior, so the bar is lower. The description adds valuable context about the public-only boundary, explicitly listing excluded data types (phone numbers, addresses, staff contacts, applicant records) and the shape of heroStories. No contradiction with 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?

The description is three sentences: the first front-loads what is returned and why, the second covers when to use it, and the third sets boundaries. Every sentence earns its place with no filler or redundancy.

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 no parameters Morphic, an output schema present, and annotations already covering safety, the description still adds the key selection triggers, the public-only guarantee, and story fields. Nothing needed to invoke this zero-input read tool 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?

The tool has zero parameters and an empty input schema, so there is no parameter burden for the description to carry. The description reinforces this with 'Requires no input', which is sufficient.

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 ('Retrieve') and resource ('public organization profile of VA Heroes PH'), with a detailed list of fields and hero stories. It clearly distinguishes this tool from program/FAQ/hero-path siblings by its focus on organization-level public information.

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 explicit trigger scenarios ('when a visitor asks who VA Heroes PH is, what it does, whether it is credible, where to follow it, or where to apply') and states what it does not return. It does not explicitly name sibling tools as alternatives, but the usage context is otherwise clear and actionable.

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=true and idempotentHint=true, but the description adds meaningful behavioral detail: query is case-insensitive and matched against both question and answer, limit caps results, and the return structure { total, count, items[] } with verbatim fields. The critical caveat about not generating answers when no match occurs is a valuable disclosure beyond any structured field.

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 longer than average but well-structured: purpose first, then use cases, then parameter semantics, then return format, then the no-answer caveat. Every sentence adds value, though it could be tightened without losing 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?

Given the tool has an output schema, full schema parameter coverage, and safety annotations, the description covers all remaining essentials: matching semantics, return structure, and the important limitation about not generating answers. An agent has everything needed to call this tool correctly and interpret results.

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% with descriptions for both parameters, but the description enriches them: it explains that 'query' is case-insensitive and searched against both question and answer, and that 'limit' caps results. These details are not present in the schema and directly affect how the agent constructs calls.

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 action ('Search the published VA Heroes PH FAQ entries') on a clear resource, and enumerates the exact question domains it covers (who can apply, required experience, skills, equipment, costs, etc.). It is immediately distinguishable from sibling tools like get_program_information or get_hero_paths, which address different resources.

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?

Provides explicit when-to-use guidance by listing the question categories it supports, and explicitly states when NOT to use it: 'It does NOT generate answers: when nothing matches, the list is empty — say so or use another tool rather than inventing an answer.' This gives the agent a clear decision boundary.

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