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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: changes derive from native totals rather than sums of breakdowns, unavailable or partial values produce no calculated change, and cohort maturity and reporting delays still apply to results.

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 compact sentences, front-loaded with the core operation and scope before the caveats about native totals and partial values. No filler sentences, though the list of invariants is dense and could be skimmed past.

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 17-parameter read-only analytics tool with full schema coverage and an output schema, the description covers the operation, the default comparison window, and the key caveats about totals and partial data. The only meaningful omission is an explicit pointer to adjust_run_report for non-comparison reporting.

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 baseline is 3, but the description contributes semantics the schema does not encode: periods must be equal length and both sides must share identical metrics, filters, OS and measurement settings. Those cross-parameter constraints materially help correct invocation.

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: comparing two equal-length periods for one Adjust application with identical metrics, filters, OS and measurement settings. It doesn't name adjust_run_report as the non-comparison alternative, so the boundary against the closest sibling is left implicit.

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 establishes the comparison behavior (defaults to the immediately preceding period) and the requirement that both periods use identical metrics/filters/settings, which implies when this tool is appropriate. However, it never explicitly says when to use this instead of adjust_run_report, so the routing decision is inferred rather than stated.

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, openWorld and non-destructive, so the bar is low, and the description still adds real context: results are permission-gated by Adjust, scoping is limited to an allowlisted application, and the metric list is partial rather than complete. That tells the agent to treat the output as an incomplete, entitlement-dependent catalog rather than a definitive one.

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, both front-loaded with the catalog scope before the permission and completeness caveats. Slightly dense phrasing ('documented standard', 'example metrics') costs a little clarity but nothing is padding.

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 no explanation, and the description covers scope, entitlement limits, and incompleteness. The remaining gap is the relationship to the report tools, which the description never states.

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 one parameter at 100% schema coverage, so the schema already carries the semantics ('Exact Adjust application token from ADJUST_APP_TOKENS'). The description only restates the scoping ('one allowlisted application') without adding format, fallback, or error behavior, which matches the baseline of 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 names a specific verb ('Read') and resource (standard Adjust dimensions and example metrics, plus event metrics for one application), so the catalog/discovery nature is clear. It does not explicitly differentiate itself from adjust_list_events, which is adjacent in scope, leaving a small ambiguity about what 'event metrics' means here versus that sibling.

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 call that precedes adjust_run_report or adjust_compare_periods, but no sentence says when to call it or when to prefer a sibling. The 'not exhaustive' caveat hints at follow-up behavior without giving direction.

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 open-world, so the safety profile is covered. The description adds genuinely new behavior: results are scoped to the ADJUST_APP_TOKENS allowlist and applications outside it are never returned, which tells the agent it may get a subset rather than all apps.

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 zero waste that front-loads the resource and follows with the scoping and allowlist clause. Nothing is repeated verbatim from the title.

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 the description needn't explain return fields, and it still notes native currency and configured operating systems. For a zero-parameter read tool this is close to complete, with only the lack of guidance relative to the sibling list/catalog tools as a 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 the schema is complete, so there is nothing for the description to compensate for. Baseline of 4 applies; the description correctly avoids inventing filtering options that do not 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?

States a specific verb and resource ('List the Adjust applications') and scopes it precisely to what the token can read plus the allowlist constraint. It does not name a sibling, but 'applications' is inherently distinct from the events/catalog/report siblings, so an agent can select it without confusion.

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: it's the enumeration call for apps an agent already knows about. There is no explicit when-to-use versus adjust_list_events or adjust_get_catalog, and no stated preconditions or exclusions beyond the allowlist filter.

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 declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered and the description only needs to add context. It does so by disclosing that results are scoped to one allowlisted app and that three distinct identifier namespaces exist (base slugs, activityMetric IDs, event tokens) whose definitions must not be mixed. It says nothing about pagination or result volume, but with an output schema present that is minor.

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 with no filler, and the core capability is front-loaded before the caveats. The middle clauses are dense ('ordinary activity-count metric IDs and app-specific event tokens') but every sentence carries distinct 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?

For a two-parameter read tool with full schema coverage, complete annotations and an output schema, the description supplies the domain context an agent actually needs: what kinds of identifiers come back and which one feeds counts. The only real gap is ordering or result-size expectations, which is modest given the output schema.

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 both appToken and search documented in the schema itself, so the baseline of 3 applies. The description reinforces the app scoping ('for one allowlisted Adjust app') but never mentions the search filter or how matching behaves. It adds nothing the schema does not already carry for parameters.

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 concrete verb plus a precise scope: 'Discover native event base slugs, ordinary activity-count metric IDs and app-specific event tokens for one allowlisted Adjust app.' That is far more specific than the name alone, which only says 'list events.' It does not explicitly name a sibling, though the line about the event base slug not being a report metric implicitly routes the agent away from adjust_run_report, so it falls short of full sibling differentiation.

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?

Guidance is present but is about field interpretation rather than tool selection: 'Use activityMetric for counts; the event base slug alone is not a report metric' and 'Keep SKAdNetwork and aggregate revenue definitions separate.' These are genuinely useful caveats about what identifier to carry downstream, but there is no explicit statement of when to call this instead of adjust_run_report or adjust_get_catalog, or of prerequisites such as needing a token from ADJUST_APP_TOKENS first.

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 cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the description does not need to. It goes further by disclosing result semantics that matter operationally: native totals and warnings are preserved, missing metrics are null rather than zero, ratios are native fractions, and truncation is explicit so a partial result must not be treated as a complete extraction.

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 tight sentences with the core purpose front-loaded and no filler. A couple of the sentences (null handling, native fractions) read as output-contract statements that partly duplicate what an output schema would express, but they are not 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?

With a full schema, rich annotations and an output schema present, the description covers the genuinely risky behaviors an agent needs: truncation, nulls, ratio units, and consistent settings across comparisons. The remaining gap is routing guidance against adjust_compare_periods, which no structured field supplies.

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% and every parameter already carries a description, including limit-vs-truncation, filter operators, and dimension/metric compatibility, so the schema does the heavy lifting. The description only reinforces the currency/UTC-offset and attribution-option defaults; it adds little parameter-specific meaning beyond that.

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?

"Read an attribution/performance report" names a specific verb and resource, and "for one allowlisted Adjust app" fixes the scope to a single app token. It never distinguishes itself from the closest sibling, adjust_compare_periods, which is the tool an agent most plausibly confuses it with.

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 only usage cue is the implicit scope (one allowlisted app), with no statement of when to choose this over adjust_compare_periods or the catalog/listing siblings. No exclusions, no preconditions such as app-token allowlisting or dimension/metric compatibility are stated in the description.

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