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

Annotations already establish readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely non-obvious behavioral context beyond the annotations: the data is cached and best-effort, alerting the agent that counts may be stale or approximate.

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, zero waste, and the identity of the resource and its contents are front-loaded before the caching caveat. Nothing is repeated from the schema beyond a brief echo of the example.

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 an output schema present, the description need not detail return values, and annotations cover read-only behavior. It is complete enough for a single-parameter read tool, missing only explicit sibling routing to get_pds_directory_info.

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 the single hostname parameter is already documented with the same bsky.network example in the schema, so the description adds no new semantics. Baseline 3 applies when the schema does the heavy lifting.

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+resource: retrieving a cached directory overview for a relay from firehose.directory, and enumerates what it contains (PDS counts, account totals). It is distinguishable from the sibling get_pds_directory_info because the resource is a relay, though it never explicitly names that sibling to disambiguate.

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?

There is no when-to-use guidance: no condition for picking this over get_pds_directory_info or count_records, and no stated prerequisites. The only context offered is the caveat 'Best-effort/cached data', which describes data quality rather than usage.

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