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

Annotations already confirm a safe, idempotent read, and the description goes well beyond them: it defines the live vs catch-up observation semantics, warns that observedAt reflects sync time rather than change time for catch-up entries, and states that caught-up changes are split out and excluded from summary figures. These are exactly the behavioral quirks an agent could not infer from 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?

Three sentences, no filler, and the core payload description leads. The sentences are dense and somewhat long, but each one carries distinct information (payload, observation semantics, exclusion from totals) rather than restating the name.

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 carries the return-shape burden and does so: it names the per-change fields, the summary totals, the provider scorecard (with its size conditionality), and the separate caughtUpChanges collection. An agent knows what it will get and how the bucket is split.

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 each of the four parameters is already documented in the schema with ranges and semantics. The description adds no syntax, format, or defaulting detail beyond that, so the baseline 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 states a precise resource — recent launch date changes from the slip ledger — and enumerates the payload (old date, new date, size of move, kind of move) plus summary totals and a provider scorecard. This is far more specific than the name alone and reads differently from siblings like launch_on_time_record or next_launches, though it never explicitly names the tool it is not.

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 'Recent launch date changes' but there is no explicit when-to-use, when-not-to-use, or routing to an alternative sibling (e.g. launch_on_time_record or launch_ledger_record). The observation/filter explanation tells the agent how the data behaves, not when to pick this tool over another.

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