Marziale Technologies

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

readOnlyHint=true already covers the safety profile, and the description adds genuinely new behavior: it interacts one question at a time, "sends nothing" (no submission/network side effect), and can return elicitation: false as a signal. Disclosing that fallback return value is real added value beyond 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?

Four short sentences, imperative and front-loaded ("Call this first, always"), with zero filler. Each sentence carries either the invocation rule, the behavior, or the fallback.

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-param interactive tool with no output schema, the description still covers the return values that matter (the answers and the elicitation: false flag). It does not explain where "the numbered questions" originate (presumably get_questions), a minor gap.

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 takes zero parameters and schema description coverage is effectively 100%, so there is nothing for the description to explain. Baseline for a parameterless tool is 4.

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 concrete action: it shows each question one at a time as a picker and returns the answers. That is a specific verb+resource an agent can act on. It does not name any sibling (get_questions, submit) to sharpen the boundary, so it falls short of the top band.

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?

"Call this first, always" gives explicit ordering, and the failure branch ("If it returns elicitation: false, ask the numbered questions in chat") tells the agent exactly what to do next. It never states when NOT to use it or names the sibling it supersedes, so it is strong but not complete.

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?

Read-only is already declared by readOnlyHint=true, and the description consistently reinforces it ('It sends nothing'). Beyond the annotation it discloses real behavior: the review is grouped by section and each missing required answer is tagged 'Missing - required'. It stops short of rate limits or error behavior, but adds solid context against a lower annotation bar.

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?

Short, front-loaded sentences with the core behavior (check, returns review, sends nothing) up top, followed by the workflow steps. The imperative dialogue line ('Ask: Do you want to change any answer?') is slightly chatty but serves the stated workflow, so little is 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?

For a read-only validation tool with 26 parameters, no output schema, and nested objects, the description usefully describes the return shape (answers listed by section with 'Missing - required' markers). An agent knows what it gets back and when to call it, with only minor gaps around error handling.

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 26 parameters, so the schema already documents fields, enums, and which are required. The description's 'missing required answer' phrasing loosely connects to the required fields but adds no syntax, format, or selection guidance beyond the schema, 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 ('Check the draft') and immediately clarifies the return behavior ('returns a review to show the person'). The contrast with `submit` ('It sends nothing', 'Before submit') gives an agent enough to tell the two tools apart, though it never names `submit` as an alternative directly.

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 ('Before submit, show the review from check_draft') and even dictates the follow-up interaction ('Ask: Do you want to change any answer? Change answers until the person is done'). It has no explicit when-not-to-use clause, but the pre-submit framing is clear context.

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 the description merely echoes this with "Read-only," adding no context beyond the structured data. It does not describe the kind of content returned, its size, or any constraints, which matters since 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?

Two short sentences with no filler, and the read-only note is front-loaded at the end as a quick signal. It is efficient, though arguably too sparse to be fully informative.

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 simple zero-parameter tool this is minimally adequate, but with no output schema the description should say more about what "what we do and the next steps" actually returns. As written, an agent knows the operation is a read but not what content to expect.

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 takes zero parameters, so the baseline is 4; there is nothing for the description to clarify. Schema description coverage is 100% for the empty object, leaving no gap to compensate for.

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 largely restates the title ("What Marziale Technologies does") with "Read what we do," so it functions as tautology rather than a specific verb+resource statement. "and the next steps" is vague about what content is actually returned, and nothing distinguishes it from siblings like get_questions or check_draft.

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 explicit when-to-use guidance and no mention of alternatives among ask_with_picker, check_draft, get_questions, or submit. The only hint is that it is a read operation, which the annotations already imply.

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 the description's 'Read-only' is consistent with that. Beyond the annotation it discloses real behavioral context: the gating dependency on ask_with_picker's elicitation flag, the ordering constraints, the interaction rules, and the 1200-character cap on long answers. It stops short of explaining what the returned payload looks like, which keeps it at a 4 rather than 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?

The purpose and routing rule are front-loaded correctly and the procedural instructions are tight, but the bulk of the description is a verbatim enumeration of the entire questionnaire, choice lists, and question branches. That content is arguably the tool's payload rather than tool documentation, so the description is dominated by material that an output schema would normally carry; it is defensible but far from tight.

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-parameter, read-only tool with no output schema, the description carries the full burden and does supply the branching questions, the answer options, the mandatory/optional markers, and the character limit. It is essentially complete for the agent's task, with only the ambiguity of embedding return content in the description keeping it below a 5.

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 takes zero parameters (empty object schema), so there is nothing for the description to disambiguate and the baseline of 4 applies. No parameter-level meaning is missing because no parameters exist.

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 opening sentence names a specific verb and resource ('Get the questions, choices, and rules') and immediately distinguishes the tool from its sibling by stating it is the fallback when ask_with_picker returns elicitation: false. An agent can tell exactly what this tool provides and when it is the right one to call without opening any other 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?

It gives explicit conditional routing against a named alternative ('Call ask_with_picker first. Use this list only if ask_with_picker returns elicitation: false') and then prescribes the interaction protocol: one question at a time, choices shown verbatim as a numbered list, follow-up on 'Other', preserve the person's words. When-to-use, when-not-to-use, and how-to-use are all stated, not inferred.

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 declare write/open-world/non-idempotent, and the description adds genuinely non-structured behavior: this is an outbound transmission to an external company that must be gated behind human review and consent. It does not warn that a repeat call creates another submission (idempotentHint=false) or what happens on failure, which keeps 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?

Two sentences, no filler, with the action front-loaded and the gating condition immediately after. Every clause earns its place.

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 30-parameter, nested-object terminal submission with no output schema, the description covers the crucial missing piece the schema cannot: the consent sequence that must precede the call. It omits any post-submission expectation (confirmation, errors, duplicate handling), so it is strong but not fully 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?

Schema description coverage is 100% across all 30 parameters, so the schema already carries the field semantics; baseline is 3. The description only loosely reinforces what review_shown/legal_and_privacy_shown/person_said_yes mean by tying 'the review' to check_draft, and adds nothing for the other 27 fields or the nested object keys.

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 with a destination: 'Send the request to Marziale Technologies.' An agent can tell this is the terminal submission step, distinct from get_questions/get_offerings/check_draft, though no sibling is named for 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, hard precondition: 'Use only after the person saw the review, the legal line, the privacy line and link, and said yes.' This is a clear when-to-use gate that maps to the three required booleans. It stops short of naming alternatives (e.g., check_draft/fix_draft) explicitly, which is what a 5 would require.

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