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

With no annotations, the description does add real behavioral context: it discloses that the result is a period-over-period comparison (last N days vs. the N before), that it counts first-time rather than repeat downloads, and that `days` is capped at 1-30. It does not cover auth requirements, aggregation granularity, or what the response contains.

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 tight sentences with the metric and comparison logic front-loaded, followed by the filtering and range constraints. 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?

There is no output schema and no annotations, so the description is the only source of truth, yet it never says what the return looks like — per-day series vs. totals, per-app breakdown, or units. For a metric-reporting tool with zero structured support, that is a meaningful 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?

Schema coverage is 0%, so the description must carry the parameters, and it does: `app` is a substring match against title, SKU, or Apple id with null meaning all apps, and `days` is bounded to 1-30 whole days. Only the default value (7) is left to 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?

Names a specific metric ('first-time downloads') from a specific source ('App Store Connect Sales and Trends') and states the comparison window. An agent can distinguish it from proceeds/subscribers/events by the resource, though no sibling is named explicitly.

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?

Explains the `app` filter behavior ('leave it out for all apps') and the valid `days` range, which implies usage but never states when to pick this tool over `proceeds` or `subscribers`. Usage is inferable from the metric name rather than guided.

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?

With no annotations, the description carries the full burden, and it does disclose two real behavioral traits: the comparison window ('`days` whole days against the `days` before') and the default enumeration behavior ('otherwise the top 50 events'). It stops short of stating read-only/safety profile, auth or project-access requirements, rate limits, or the shape of the returned comparison.

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 dense sentences, front-loaded with the operation and comparison window before parameter meanings. Every clause carries information; nothing is repeated from the schema or padded.

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 three-parameter read tool with no annotations and no output schema, the description covers parameter meaning, default behavior, and the comparison basis, which is nearly everything needed to call it correctly. The main gap is what the response actually contains (per-event current/prior counts, deltas, ordering), which the absence of an output schema leaves unstated.

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 0%, so the description must compensate and largely does: it defines `days` as the window width for both the current and prior period, `project` as the numeric PostHog project id, and `names` as a filter with top-50 fallback when null. The only friction is that `project` is typed as a string in the schema while described as numeric, a minor inconsistency.

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 resolves an otherwise vague tool name ('events') into a specific operation: PostHog event counts over the last `days` whole days compared against the preceding `days` window. The resource and the comparison semantics are clear, and no sibling tool (downloads, proceeds, subscribers, revenuecat_projects) overlaps, so explicit differentiation isn't 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?

Usage is implied by the stated output (period-over-period event counts for a PostHog project), but there is no explicit when-to-use or when-not-to-use guidance, nor any mention of how it relates to the other analytics siblings. An agent can infer intent but is given no routing rules.

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?

With no annotations, the description must carry the behavioral burden. It does disclose the data source, currency dimension, and comparison semantics, plus the 1-30 day constraint — meaningful context. It omits whether this is a read-only report, what permissions/reporting access are needed, data freshness/lag, and whether proceeds are gross or net of Apple's cut.

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 comparison semantics front-loaded and parameter details following. The phrase 'the last `days` against the `days` before' is slightly compressed and requires a second read, but nothing 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?

There is no output schema, so the description should sketch the return shape; 'by currency' hints at grouping but doesn't say whether results are per-currency totals, per-app breakdowns, or deltas/percentages. For a zero-annotation, zero-output-schema tool, that leaves an agent guessing about what it will actually receive.

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 0%, so the description must compensate, and it largely does: `app` is defined as a substring match on title, SKU, or Apple id with omit-for-all behavior, and `days` is bounded to 1-30. The only gap is that the default (7) is only visible in the schema and not reinforced, and the matching behavior for multi-app ambiguity isn't addressed.

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 metric (developer proceeds) from a specific source (App Store Connect Sales and Trends) with an explicit comparison window (last `days` vs. the `days` before). That distinguishes it from siblings like downloads, subscribers, and events, though the verb is implied rather than stated ('proceeds from...' rather than 'fetch/calculate proceeds').

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 explains the optional `app` filter ('leave it out for all apps') and the day range, which is useful usage context. But there is no guidance on when to pick this over `downloads` or `subscribers`, nor any prerequisites (App Store Connect credentials, data lag) that would tell an agent whether it can call it now.

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?

With no annotations, the description carries the burden and does disclose that results are limited to what “this key can read,” which is useful permission-scope context. It implies a read-only operation and states returned fields, but it does not cover pagination, empty results, or explicit safety behavior.

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 compact sentence that front-loads the resource and its scope. Every clause contributes useful information: access scope, returned fields, and how to use the ID with another tool.

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 tool with no output schema, the description gives the essential return fields (id and name), access scope, and a clear downstream use. It could be slightly more complete by mentioning ordering, pagination, or what happens when no projects are visible, but the core information is present.

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. The description appropriately does not invent input semantics, and the empty schema already makes the parameter situation clear.

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 identifies a specific resource, RevenueCat projects, and states the scope and return fields: projects this key can read with id and name. It also links the output to the `subscribers` sibling, though it does not explicitly use a verb like “list” or differentiate from all other siblings.

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 phrase “Use an id with `subscribers`” gives downstream context, implying this tool supplies project IDs needed by the subscribers tool. However, it does not explicitly say when to call this tool versus alternatives or describe prerequisites beyond that implication.

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?

No annotations are provided, so the description carries the full behavioral burden. It describes the metric set and the current-vs-previous-window comparison, but never states that this is a read-only report, what the window length is, whether data is cached or rate-limited, or what the response looks like.

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 metric inventory, and no filler. Dense but every clause carries information about what comes back.

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 enumerates return values, and it clarifies the one required parameter. However, the window parameter that determines the entire time scope is left undefined, which is a material gap for calling the tool 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 description coverage is 0%, so the description must compensate. It explains `project` as a RevenueCat project id, but never mentions `days`, its unit, or its default of 7 — 'this window' is gestured at without tying it to the parameter that controls it.

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 the specific metrics returned (active subscriptions, trials, MRR, 28-day revenue) plus the period-over-period comparison, so the resource and output are clear. The verb is implicit rather than stated ('returns/reports'), and it never names a sibling like `proceeds` to draw the boundary, so it falls 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?

Listing the metrics implies when the tool is appropriate, but there is no explicit when-to-use, no exclusions, and no routing against `proceeds` or `events`, which overlap on revenue figures. The agent must infer the choice from the metric names alone.

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