dpdp-compliance

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful content-level disclosure (that each date carries confidence and review status), but says nothing about freshness, source authority, or how the data is maintained.

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?

A single sentence with the resource named first and a colon-delimited enumeration of contents. Nothing is wasted and it 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?

No output schema exists, so the description must convey return shape—it does by naming the dates, the obligation groups, and the confidence/review metadata. For a zero-param static lookup this is close to complete, missing only freshness or provenance notes.

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?

Zero parameters, so there is no parameter semantics burden; baseline 4 applies. The description cannot and need not add parameter detail.

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 concrete resource (key dates under India DPDP Rules, 2025) and enumerates the scope of those dates: notification date and the commencement of obligation groups (Consent Managers, Data Fiduciary duties, penalties). This clearly distinguishes it from dpdp_obligations and dpdp_penalty_ceilings by content, though it never references those siblings by name.

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 implied: retrieve key compliance dates. There is no explicit when-to-use, when-not-to-use, or routing to the sibling tools (dpdp_obligations, dpdp_penalty_ceilings), which an agent choosing between three DPDP tools would benefit from.

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 openWorldHint=false, so the safety profile is covered structurally. The description adds that results carry 'confidence and review status', which hints at potentially unevaluated or variable-reliability content, but it does not explain what those fields mean, how results are ranked, or how many are returned.

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 core purpose front-loaded and the return characteristics in a compact trailing clause. The parenthetical topic list is somewhat long but earns its place by scoping the lookup.

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 lookup with no output schema, the description covers purpose, example inputs and the shape of the return well enough to call it correctly. It stops short of explaining result ordering, count, or how to interpret confidence/review status.

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 and schema description coverage is 100%, so the baseline is 3. The description does supply additional example keywords beyond the schema's 'breach notification' and 'grievance', which helps an agent choose vocabulary, but it adds no syntax, granularity or matching-semantics detail.

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 ('Look up DPDP Act sections and Rules by topic') and gives a concrete topic list spanning breach, consent, grievance, children, processor contract, erasure, safeguards and transfers. It is clearly distinguishable from the sibling tools dpdp_key_dates and dpdp_penalty_ceilings by domain, though it never explicitly contrasts itself with 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 implied by the topic examples – an agent can infer this is the tool for substantive obligations rather than dates or penalties. However, there is no explicit when-to-use/when-not statement, no guidance on what to do when a lookup returns nothing, and no named alternative 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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real interpretive value beyond the annotations by warning that these figures are ceilings rather than a prediction of what any business would actually pay — exactly the misuse an agent would otherwise make.

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, zero filler, with the substance front-loaded and the caveat placed second where it qualifies the whole. 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 no-parameter, no-output-schema reference tool, the description is essentially complete: it says what content is returned and pre-empts the obvious misreading. Only a bare hint about result shape or scope (statute version/jurisdiction) 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 takes no parameters, so there is no parameter semantics to explain and the baseline of 4 applies. The description correctly spends none of its text restating an empty input 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 names a specific resource — the maximum penalties in the Schedule to the DPDP Act — plus the Board's aggravating factors, so an agent knows exactly what content comes back. It is a noun phrase rather than a verb+resource, and it does not explicitly contrast itself with dpdp_key_dates or dpdp_obligations, though the subject matter is plainly distinct.

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: an agent can infer this is the tool for questions about statutory fine amounts, but there is no explicit when-to-use or when-not-to-use statement and no pointer to siblings. For a zero-parameter reference lookup the cost of that omission is modest, so a middle score is fair.

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 establish readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuine behavioral value beyond that: it discloses the exact return contents (tier count, INR pre-tax pricing, limits, trial length) and that data is 'read live from the same source as the pricing page,' signaling freshness rather than caching — important 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 sentences, no filler: the first front-loads exactly what is returned, the second supplies the freshness guarantee. Every clause carries 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?

With no output schema, the description carries the return-value burden and does so by enumerating contents; annotations cover the read-only, non-open-world profile. There are no parameters and no mutation concerns, so an agent has everything needed 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?

Zero parameters, so there is no parameter semantics to explain; the baseline for a no-arg tool applies. Schema coverage is also 100%, so nothing is left undocumented.

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 resource (OpenProof's public pricing plans) and enumerates exactly what it returns: three annual tiers, INR prices before taxes, inclusions/limits, and trial length. It is clearly distinct from all four siblings (dpdp_* regulatory queries, scan_site), though the retrieval verb is implied by 'Read live' rather than stated up front.

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 makes the tool's subject matter obvious, so usage is strongly implied — call it when you need current OpenProof pricing. However, it never states when to use this versus alternatives or any exclusions/conditions, leaving the agent to infer the trigger.

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?

Goes well beyond annotations by disclosing the rate limit (a few scans per hour per client), site-owner opt-out handling, the read-only-on-target-page scope, and the crucial caveat that this is an automated surface check and not an audit or legal advice. Annotations declare openWorldHint and idempotentHint but say nothing about limits or opt-outs, so the description adds substantial value.

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 and return payload are front-loaded in the first sentence, followed by behaviour, caveats, and operational constraints in tight sentences with no filler. It is dense but every clause contributes information an agent needs.

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 correctly enumerates the returned signal categories so the agent knows what comes back. It also covers limits, opt-outs, response-shape caveats, and batching constraints, leaving no material gap for a single-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% and there is a single parameter, so the schema already carries the load; baseline 3 applies. The description slightly enriches it by stressing the address must be public and singular, but adds no format or edge-case guidance beyond the schema's example.

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 ('Run OpenProof's website scan on one public web address') and enumerates the exact signals returned, so the agent knows precisely what the tool produces. It is clearly the only action tool among information-retrieval siblings, so differentiation is easy without opening a 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 concrete invocation constraints: one public web address, send as its own request rather than inside a batch, and a per-client hourly rate limit. It does not explicitly contrast against any sibling by name, but the surrounding tools are all static DPDP reference lookups, so the usage context is unambiguous.

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