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

The description adds vital operational context beyond the annotations and schema. It specifies that 'Changes use native totals, never sums of breakdowns' and details limitations regarding partial values and cohort maturity, which are critical behavioral constraints for an AI agent.

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 highly concise. It uses two sentences to articulate the complex requirements, technical constraints (native totals), default behaviors, and limitations without any superfluous language.

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 complex, constraint-heavy comparison tool, the description is complete. It covers the required data consistency (metrics, filters, OS), technical calculation methods, and operational limitations, providing everything needed for safe and correct invocation.

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?

Given the 100% schema coverage, the description focuses on the semantic *constraints* of the parameters (e.g., all settings must be identical) and the operational logic of the tool (e.g., comparison defaults), which is highly valuable to a developer/agent.

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 tool's purpose is clear: to compare two time periods. It specifically frames the comparison around 'equal-length' periods and requires an 'allowlisted Adjust application,' making it distinct from general reporting tools like adjust_run_report.

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 provides extremely explicit usage guidance by requiring that the comparison use 'identical metrics, filters, OS and measurement settings.' It also clearly defines the default behavior (immediately preceding period), guiding the user when to omit the `comparison` field.

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 read-only, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely useful context beyond that: access is gated by Adjust permissions, spend/revenue visibility may be restricted, and the returned metric list is explicitly non-exhaustive, which prevents an agent from treating it as a complete enumeration.

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 action front-loaded and the caveats about permissions and non-exhaustiveness placed after it. Dense but efficient.

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?

An output schema exists, so return values need not be described here. Combined with annotations, the description covers what an agent needs to call this safely: it is a read, it is scoped to one app, and results may be filtered by permissions and are not guaranteed 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 a single parameter and the schema coverage is 100%, with the schema already explaining the app token and the distinction from ad accounts. The description reinforces scoping to an allowlisted application, but adds no format or sourcing detail beyond what the schema provides, so the baseline 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?

States a specific verb and resource: reads the Adjust catalog of dimensions and metrics, scoped to one application. It is distinguishable from siblings such as adjust_run_report and adjust_list_events by being a discovery/catalog read rather than a data fetch. The phrase 'example metrics' is a little soft, but the intent is clear.

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 a discovery step before running a report, but the description never says when to call it versus adjust_list_events or adjust_run_report, nor states prerequisites beyond the app token.

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 this as read-only, idempotent, non-destructive, and open-world. The description adds meaningful context by disclosing that only allowlisted applications are returned and that native currency and configured operating systems are included.

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 a single well-formed sentence that front-loads the action and resource. Every clause adds relevant information: token scope, allowlist behavior, and returned attributes.

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 listing tool with rich annotations and an output schema, the description covers the essential behavioral constraints. It discloses the allowlist boundary and useful return fields without redundantly explaining schema-covered output details.

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, so the schema has no parameter semantics for the description to explain. The baseline for a parameterless tool applies; nothing in the description suggests hidden parameter behavior.

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: 'List the Adjust applications.' It also specifies the token-scoped allowlist and the returned attributes, but it does not explicitly differentiate this tool from siblings such as adjust_list_events or adjust_get_catalog.

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 scope is applications in ADJUST_APP_TOKENS readable by the token, which implies when the tool is useful. However, it gives no explicit when-to-use guidance, no exclusions, and no mention of alternatives such as adjust_get_catalog or adjust_list_events.

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, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds genuine domain context beyond that: the app must be allowlisted, the returned identifiers have different downstream semantics, and certain definition families must not be conflated. It omits pagination/result-cap behavior, which is why it is not 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?

Three tight sentences with the purpose front-loaded and no filler. The phrasing is jargon-dense (base slug vs activity-count metric ID vs event token) but each clause carries a distinct constraint.

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?

An output schema exists, so return values need not be spelled out, and the description still characterizes the three identifier kinds an agent will get back. For a two-parameter read-only lookup this is nearly sufficient; only result-size/pagination expectations are unaddressed.

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 both appToken and search are documented in the schema; a baseline of 3 applies. The description reinforces the app-token scoping ('one allowlisted Adjust app') but adds nothing about the search filter or the identifier format, so it does not exceed 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 names a specific verb ('Discover') and concrete resources ('native event base slugs, ordinary activity-count metric IDs and app-specific event tokens') scoped to 'one allowlisted Adjust app'. An agent can tell this is a discovery/enumeration tool rather than a reporting one. It does not explicitly name a sibling (e.g. adjust_get_catalog) to differentiate against, which keeps this from 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?

It gives concrete downstream guidance ('Use activityMetric for counts; the event base slug alone is not a report metric') and a segmentation warning about SKAdNetwork vs aggregate revenue, which helps the agent choose the right identifier. However, it never states when to call this versus adjust_get_catalog, adjust_list_apps, or adjust_run_report, so sibling routing is left to inference.

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 this as a safe, read-only, idempotent, non-destructive operation. The description adds useful behavioral context beyond annotations, including preservation of native totals/warnings/options and the warning that truncated or partial results are not complete extractions.

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 short, front-loaded with the core purpose, and each sentence contributes useful semantics. The final truncation warning is slightly redundant in wording but still earns its place as a usage caveat.

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 full input schema, annotations, and an output schema carry most of the operational detail, so the description does not need to explain return values or parameters. However, for a complex report tool with a compare-periods sibling, it should do more to explain when this tool is preferable to alternatives.

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 all 16 parameters in detail. The description adds only high-level semantics such as preserved currency and UTC offset, so the baseline 3 is appropriate.

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 and resource: reading an attribution/performance report for one allowlisted Adjust app. It is clear enough to distinguish from list/catalog sibling tools, but it does not explicitly contrast with adjust_compare_periods.

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 provides no explicit when-to-use guidance, no exclusions, and no named alternatives. An agent must infer selection from the tool name and purpose alone.

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