MAX Data Value Check

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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description still adds substantive context the annotations cannot: the 0-100 scoring output shape, that red flags cover privacy/consent/history length, that no dollar valuation or outreach occurs, and that answers are not persisted.

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 the scoring action and its outputs, followed by usage, then hard exclusions and a privacy warning. Every sentence contributes; it is dense but not padded, though the privacy sentence partially repeats the 'does not store answers' point.

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 11 parameters and no output schema, the description must carry the return-value burden and does: it names the score range, the factor breakdown, buyer-type suggestions, red-flag categories and next steps. Combined with the full schema coverage and explicit scope limits, an agent has everything needed to call it and interpret the result.

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% with 9 of 11 params enumerated, so the schema carries the field-level detail and a baseline 3 is the floor. The description adds real semantic constraint on how to fill those fields: answers must be coarse multiple-choice, and names, contact details, patient information or the raw data itself must never be submitted — which directly governs the health/personal-info flags.

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 output ('Scores how ready ... 0-100') plus the input mode ('using only multiple-choice answers'), and enumerates the returned content (factor breakdown, buyer types, red flags, next steps). None of the siblings (term explanations, checklists, handoff links, disclosures) overlap with this scoring function, so an agent can route to it 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 an explicit trigger ('Use when someone asks whether their company's data could be sold or licensed, or what it would take') and explicit exclusions ('does not estimate a dollar value, make an offer, contact anyone, or store answers'). This tells the agent both when to call it and what adjacent requests it should not be used for.

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, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the not-found path returns the glossary's term list, which shapes how an agent should react to an empty result. It does not say whether matching is fuzzy or case-sensitive, which is a minor remaining gap.

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: the first defines the output, the second covers the error path, the third gives the trigger. Nothing is redundant and the most important information leads.

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?

A single-parameter lookup with no output schema, fully covered: verb, example inputs, trigger condition, and fallback behavior are all present. No further An agent would need to call 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?

Schema coverage is 100%, so the baseline is 3, but the description adds value by listing six representative term types, signalling that the parameter must be a glossary-recognizable term rather than free text. That constrains agent input behavior in a way the bare schema string example does not.

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 ('gives a short plain-English definition of a data licensing term') and enumerates concrete example terms, so an agent knows exactly what output shape to expect. None of the sibling tools (readiness checks, rights checklists, handoff links, disclosure lists) overlap with glossary lookup, so no disambiguation is needed.

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 when someone asks what a data licensing term means' gives a clear trigger condition, and the fallback ('if the term isn't in the glossary, returns the list of available terms') tells the agent what happens on a miss. It stops short of naming an alternative tool, but no plausible sibling alternative exists here.

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, non-destructive and closed-world, so safety is covered. The description adds genuine behavioral context beyond that: it is 'general information, not legal advice' and it 'stores nothing', which tells the agent how to frame and caveat the output rather than presenting it as a legal opinion.

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, front-loaded with the return value, and the enumeration in the first sentence earns its length because there is no output schema to reveal the checklist's contents. Slightly dense but no filler.

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 output schema, the description usefully sketches what the checklist contains and adds the legal-advice disclaimer an agent needs in order to relay results responsibly. It does not explain how the five optional parameters vary the output, a minor gap for a six-parameter 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 every parameter is already documented in the schema; baseline 3 applies. The description adds only one small link — that the returned privacy laws are keyed to 'the selected data types' — but says nothing about how hq_region, sells_to, contains_personal_info or contains_health_info shape the checklist.

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 — 'Returns a step-by-step checklist' — and enumerates the checklist's scope (ownership/contracts, privacy policy, de-identification, vendor terms, provenance, permitted uses, applicable privacy laws). That is far more specific than the title. It does not explicitly name or differentiate from siblings like check_data_readiness or explain_data_licensing_term, so it stops 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?

'Use when someone asks what permissions, consents or legal checks they need before selling or licensing business data' gives a clear triggering context. There is no explicit when-not guidance or pointer to the sibling tools (readiness check, term explainer, disclosure list) that an agent might confuse with this 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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description adds substantial context beyond them: no message is sent without the owner, the owner controls the send, PII must not be passed to this tool, and the referral reward goes only to the verified human ambassador, never to an agent or wallet. It also imposes a disclosure duty on the caller. Nothing here contradicts the 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 definition is front-loaded with the return value and then layers usage, privacy, referral and disclosure rules in a logical order. It is longer than average, but nearly every sentence carries an operational constraint, so only the referral/reward explanation is slightly redundant.

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, and the description still says what comes back: a link that opens a prefilled text to MAX. With both optional parameters fully documented in the schema and the safety profile covered by annotations, an agent has everything needed to select and call this 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?

Schema coverage is 100%, so the baseline is 3; the description still adds meaning by explaining that the referral code credits a specific ambassador, that it defaults to the ?ref= code in the server URL, and by barring owner PII from being supplied at all. The agent_name field's anonymous-count purpose is only documented in the schema, which keeps this short of a 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 first sentence gives a concrete verb and resource: it returns a link the owner can tap to open a prefilled text message to MAX, the data agent. That is clearly distinguishable from the sibling tools (check_data_readiness, explain_data_licensing_term, get_data_rights_checklist, list_public_data_licensing_disclosures), none of which produce an outbound handoff artifact.

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 states an explicit precondition ('Use only when the owner says they want a real review or next step'), anchors it to a sibling tool ('for example after check_data_readiness'), and adds exclusions and handling rules: show the link, never send the owner's PII to this tool, pass a referral code when acting for an ambassador. Both when and when-not are covered.

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, non-destructive, closed-world behavior, so safety is covered. The description adds genuinely non-obvious context beyond that: the data provenance and weekly refresh cadence, the returned fields (filing dates and direct sec.gov links), and a crucial interpretive caveat that a match means a filing mentions the phrases, not that a deal closed or has value. It does not mention result caps beyond the limit parameter or how far back the tracker goes.

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 the tool returns and where the data comes from, then usage guidance, then the accuracy caveat. No filler or restated title text; every clause adds information an agent would otherwise have to guess.

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-only listing tool with no output schema, the description covers the essentials: scope, source, refresh cadence, returned fields, and the interpretation limit on matches. The only gaps are record depth/history and ordering of results, which are minor for this use case.

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 both parameters including ranges and defaults. The description echoes the optional company-name filter ("Optionally filter by part of a company name") but adds no matching semantics such as case sensitivity or substring behavior, and never mentions the limit parameter. Baseline 3 applies when the schema carries the parameter burden.

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 gives a specific verb and resource ("Lists public companies whose SEC filings... mention AI data licensing") and names the underlying source (MON$TER's weekly SEC EDGAR full-text tracker) plus the exact filing types covered. This is clearly distinct from the siblings, which are about readiness checks, term explanations, checklists, and handoff links rather than filing discovery.

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 states the trigger condition explicitly: "Use when someone asks which companies license data to AI or wants public examples." That is a clear when-to-use signal. It does not name a sibling alternative or state when-not to use it, but the domains of the sibling tools are far enough apart that the routing risk is low.

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