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

Annotations carry only a title, so the description bears the behavioral burden and does disclose the return shape (identity, visible areas, allowed tools, keeper rules) and a non-obvious interaction rule (no persona; keep your own identity, refer in third person). It stops short of stating side effects or that the call is a pure read, which with zero annotation coverage leaves a small gap.

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?

Front-loads the core action and the 'call first' directive before the return-value detail and behavioral caveats. It runs a bit long across several sentences, but each clause adds a distinct rule (return contents, persona policy, recall fallback), so little is wasted.

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?

There is no output schema, and the description steps in to describe the return payload, plus it covers the timing rule and the sibling routing. The main omission is parameter guidance for `scope` and any note on failure/authorization behavior, but for a zero-required-parameter bootstrap call it is nearly complete.

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 description never mentions `scope` or `kit_session_id`. With schema coverage at 50%, `kit_session_id` is explained in the schema but `scope` is a bare enum with no description, and the description does not compensate by explaining when to choose work/personal/all or how session reuse/subagent waking works. Only the enum labels themselves carry any 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?

Names a concrete action (open/query an archive) and enumerates what the call yields: identity (`you_are`), visible knowledge areas, permitted tools, and keeper rules. It differentiates itself from siblings by explicitly naming `recall` as the tool for contributing knowledge, so an agent can place it without opening any 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?

Gives an unambiguous trigger: 'Call this first in every new chat... before the first substantive answer,' even naming the host environments. It also states the alternative path — use `recall` for anything the archive should know rather than relying on model knowledge — so when-to-use and when-to-use-something-else are both explicit.

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