Log a user-visible change

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description reveals the external write side effect (creates a PostHog annotation), the singular-unit behavior, and the non-batching constraint. It also clarifies that non-code changes are valid, preventing the agent from assuming only PRs count. There is no contradiction with annotations, but it doesn't cover what happens if the same change is logged twice.

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 dense, single paragraph with every clause adding operational guidance: qualifying categories, exclusions, batching constraint, non-code emphasis, and speculative-logging policy. It is front-loaded with the core action and avoids redundant restatements of the title. Each sentence contributes to correct selection and invocation.

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?

Given the tool has five parameters, no output schema, and annotations that are thin, the description covers the critical invocations: what counts as a loggable change, how to handle uncertainty, and the one-call-per-change rule. It is complete for an agent to select and call the tool without further clarification. The return value is not described, but with no output schema that is not a significant 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 input schema already provides 100% description coverage for all five parameters, so the baseline is 3. The description adds context about what constitutes a qualifying change (non-code counts, ask user when unsure) but doesn't add syntax or format details beyond the schema. Therefore the parameter semantics are adequate but not significantly enhanced by the description.

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 ('Record ONE user-visible product change as a PostHog annotation') and clearly defines the scope by listing qualifying categories and exclusions. This makes it easy to distinguish from the sibling tool check_changes, which presumably reads/checks changes. The emphasis on 'ONE ... per call' adds precision.

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 explicit inclusion lists (pricing, copy, onboarding, packaging, email, channel) and exclusion lists (refactors, dependency bumps, tests, infra, CI, internal tooling). It states cardinality ('One change per call — never batch'), and gives a decision rule for ambiguity ('If unsure, ask the user once; never log speculatively'). This covers when and when-not to use the tool, though it doesn't explicitly compare against check_changes.

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