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

Annotations already cover read-only/idempotent/open-world, but the description adds substantive traits the annotations cannot convey: confirmed-block records only (mempool writes lag), expired records included and flagged with the warning that their names can be reclaimed, and roughly one-minute result caching. It also clarifies that only fingerprints and metadata are returned, never content.

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 opening clause front-loads verb, resource, and return shape before any caveats, and every subsequent sentence carries real information. It is on the long side and the 'Read-only, no sign-in needed' phrase partly restates the readOnlyHint annotation, which costs a bit of density.

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 needn't enumerate return fields, yet it still characterizes the returned view (confirmed-only, expired-flagged, hashes plus metadata, no content). For a tool with three optional params and eventual-consistency behavior, nothing an agent needs 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 coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: it frames the result set as a page-oriented chain view where `offset` follows `next_offset`, and reinforces the `github_id` omission semantics as a signed-in fallback rather than an error case.

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 and resource (list every record under one GitHub id), names the exact naming scheme it returns (`ai:gh:<id>` and `ai:gh:<id>:mem:<hash>`), and orders results (newest first). It also distinguishes itself from `read_record` by explaining that this is where the hashes needed by that sibling come from.

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?

Gives a concrete triggering scenario ('an agent starting a fresh session finds what it anchored before') and the exact handoff to `read_record`. It also states the condition for the optional parameter (omit `github_id` to list your own when signed in) and points at `whoami` for obtaining an id.

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