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

Annotations already declare this as a non-read-only, open-world, non-idempotent, non-destructive operation, so the safety profile is partly covered. The description adds genuinely useful context — that sharing grants read or read+write access to every member of a space or to a single account — but it truncates before clarifying the write level and says nothing about expiration (the 'days' param implies time-limited grants) or how to undo a share.

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 single sentence is front-loaded and free of filler, but it ends mid-clause ('read, or read and...'), which is a structural defect rather than brevity. The most decision-relevant detail — what permission levels exist — is exactly what got cut.

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?

For a 6-parameter, no-output-schema, open-world mutation tool, the description establishes the actor, target, recipients, and permission axis, which is the essential skeleton. It is still incomplete: grant duration, the note field, and the ability to later revoke are unaddressed, and the truncated ending leaves the write permission ambiguous.

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 0% across 6 parameters, so the description carries the full burden and only partially delivers: it maps to 'space', 'acct', and 'write' conceptually without naming them or their formats. 'days' (presumably grant duration) and 'note' are entirely unexplained, leaving two of six parameters with no semantics anywhere.

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 ('Share a folder of the machine you own') plus the two recipient modes (space vs one account) and the permission level (read, or read and ...). An agent can distinguish it from doc_list/doc_read/doc_write/doc_revoke from the text alone, though the sentence is cut off before the read/write distinction completes.

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?

The space-vs-account choice is described as an option, which hints at a selection decision, but there is no explicit when-to-use guidance and no mention of alternatives such as doc_revoke for unsharing or doc_shares for inspecting existing shares. The agent must infer the lifecycle context.

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