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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral context: the {project_id} path placeholder is replaced with the default project, which is a non-obvious behavior. It does not describe response format, but with no output schema and a generic GET tool, the description provides adequate transparency beyond 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 description is two sentences with no wasted words. The primary purpose is front-loaded, the scope boundary is stated immediately, and the {project_id} substitution detail is placed at the end where it belongs. Every sentence 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 generic GET-all-endpoints tool with readOnlyHint=true and openWorldHint=true, the description covers the essential context: what it does, when to use it, and the key path substitution behavior. It does not explain response format or error behavior, but for a passthrough GET tool with no output schema, this is a minor gap. The sibling tools are not explicitly differentiated, but the HogQL contrast helps.

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 (path and params). The description adds the important detail that {project_id} in the path is replaced with the default project, which adds meaning beyond the schema. However, it does not elaborate on the params object structure beyond what the schema provides, so a 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 ('GET') and resource ('any PostHog REST endpoint'), and explicitly scopes it to what HogQL does not cover, listing concrete examples (feature flags, insights, dashboards, experiments, cohorts). This clearly distinguishes it from sibling tools like posthog_query, which presumably covers HogQL.

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 gives clear context on when to use this tool ('for what HogQL does not cover') and lists example endpoints. It does not explicitly name sibling alternatives or state when not to use it, but the contrast with HogQL and the sibling list (posthog_query) makes the usage context reasonably clear.

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 establish readOnlyHint=true, so no destructive behavior needs disclosure. The description adds the useful behavioral detail that results include event names and their last-seen timestamps, but it does not describe pagination behavior, ordering, or data freshness. This is adequate but not rich.

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 two tight sentences, front-loaded with the core purpose and followed by a relevant usage note. Every sentence earns its place, and no redundant content is present.

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?

This is a simple, read-only list operation with no required parameters and a fully documented schema. The description supplies the essential return concept (event names plus last-seen) and a usage context. It could be slightly more complete by noting response ordering or pagination defaults, but those are inferable from the 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 each of the four parameters (limit, offset, search, project_id) carrying a description and default values. The tool description adds no parameter-level meaning beyond what the schema already provides, so the baseline score 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?

The description clearly identifies the resource (event names in a project) and the specific aspect it covers (when each was last seen), with a clear title 'List event names'. It does not explicitly distinguish itself from sibling tools like posthog_property_definitions, but the resource is specific enough to avoid 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?

The description gives explicit usage guidance: 'Use it instead of guessing event names in HogQL.' This tells the agent when this tool is appropriate relative to a query alternative, though it does not explicitly mention alternatives or exclusion cases for sibling tools.

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 read-only and open-world behavior. The description adds useful behavioral context beyond the annotations by disclosing compatibility with project-scoped API keys, which affects how an agent should authenticate and interpret the returned project list. There is no contradiction with 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?

Two short sentences with no filler; the core purpose is front-loaded and the authentication note is the only additional detail. Every sentence 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 zero-parameter list operation, the description names the resource, the returned fields, and an important API-key constraint. A more explicit response shape would be helpful given the lack of an output schema, but the open-world annotation and the simple scope keep this from being a major 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 has zero parameters and the schema is trivially fully described, so the description does not need to document parameter semantics. It still adds context about the returned content (ids), which is more than the empty schema provides.

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 resource ('projects of the organization') and the key output ('their ids'), and the title supplies the verb 'List'. This is specific enough to distinguish it from sibling tools focused on event definitions, properties, queries, and replays.

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 relevant context by noting that the tool works with API keys scoped to specific projects, which implies an authentication prerequisite. However, it does not explicitly state when to prefer this tool over alternatives like posthog_api_get or posthog_query, or when it should not be used.

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=true and openWorldHint=true, covering the safety profile. The description adds no further behavioral details such as pagination behavior, response format, or rate limits, but it does not contradict 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?

Two short sentences with the core content front-loaded. The second sentence justifies why the tool is useful and is not 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?

For a listing tool with no required parameters and no output schema, the description states what will be returned (names and types), and the annotations cover read-only/open-world behavior. It does not mention pagination or search, but those are fully documented in the schema, so nothing essential 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?

Schema description coverage is 100%, so all five parameters are adequately documented in the schema itself. The description only restates the event/person distinction already encoded in the type enum, adding no new parameter-level meaning.

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: listing event or person property names in a project with their types. It is clear, but it does not explicitly contrast itself with sibling tools like posthog_event_definitions, so it relies on the resource name rather than naming the distinction.

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 an explicit usage trigger: use this instead of guessing property names in HogQL. However, it does not state when not to use it or mention alternative tools, so the guidance is clear but not exhaustive.

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 readOnlyHint and openWorldHint already annotated, the description doesn't need to restate the read-only or open-world traits. It adds valuable behavioral context by enumerating accessible tables (events, persons, sessions, groups, raw_session_replay_events) and showing a concrete query pattern, which helps an agent understand what to expect.

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 two sentences long: the first states the core function and data sources, the second provides an illustrative example. It is front-loaded with the action and resource, and every word adds value.

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 generic query tool, the description provides everything an agent needs: the dialect, the available tables, and a full sample query. Since no output schema is present, return format expectations are appropriately left open, and the annotations handle read-only and open-world behavior.

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 schema only describes the query parameter as 'HogQL query text', but the description adds concreteness by listing the exact tables and providing a working example query. This goes beyond the schema's generic description and gives the agent a clearer model for constructing valid inputs.

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 clearly states the tool runs a HogQL query against a defined set of tables Aleksandrov, and the example makes the exact syntax concrete. It is easily distinguished from siblings like posthog_event_definitions and posthog_property_definitions, which serve narrower metadata retrieval purposes.

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 gives clear context for when to use the tool: for writing arbitrary HogQL queries over the listed tables. It doesn't explicitly state when not to use it or explicitly name the sibling alternatives, but the table list implies that this is a general-purpose query tool rather than a structured endpoint.

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 convey read-only behavior, and the description adds meaningful context: results are sorted newest first, recordings older than instance retention are unavailable, and naive timestamps are interpreted in the project timezone. It does not describe auth requirements, rate limits, or the exact response shape, but those gaps are minor for a read-only lookup tool.

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 the core function front-loaded. Every sentence earns its place: ordering, watch links, retention limitation, and timezone behavior. There is no filler or repetition of schema details.

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?

All facts needed to select and invoke the tool are covered: required distinct_id, optional window bounds, limit, ordering, retention, and timezone interpretation. With no output schema, the description only minimally describes the return value via 'links to watch them,' but that is sufficient for basic invocation confidence.

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 schema has 100% description coverage, so the baseline is 3. The description adds genuine cross-parameter nuance beyond individual field docs: the from/to window parameters assume naive timestamps in the project timezone, and results are ordered newest first. This helps the agent format the time-window parameters correctly.

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 resource: session recordings for one distinct_id in a time window, with a clear ordering (newest first) and an output affordance (links to watch them). This is distinct from the sibling tools like posthog_query or posthog_api_get, which are more generic. An agent can tell exactly what this tool does 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?

The intended use is clear from context: fetch session replays for exactly one distinct_id within a bounded time window. However, there is no explicit guidance about when to prefer this over sibling tools or when it would not be appropriate. The agent must infer that posthog_query is not the right tool for retrieving watchable replay links.

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