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

With no annotations, the description carries the full load and partially meets it: it discloses the persistence layer (Cloudflare D1), the host (autocad.site) and that both view and edit URLs are returned. It omits the security-relevant behavior an agent needs — that the edit URL grants write access, whether the share is public/unauthenticated, and that cad_revoke_shared is the undo path.

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 tight sentences with the core action front-loaded and the return artifact second. The trailing 'with users or other agents' is mild padding but does not obscure the message.

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?

No output schema, and the description does cover the return shape, which is good. However, for a mutation tool with zero annotations it says nothing about prerequisites, access scope of the generated links, or expiry/revocation interaction, leaving notable gaps an agent must guess at.

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 name, apiUrl and expiresDays are already fully documented in the schema. The description references none of them and adds no format or interaction detail (e.g. what happens if name collides), 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?

States a specific verb and resource ('shares the current drawing') plus the storage backend and the artifact produced (view and edit URLs). This distinguishes it from cad_open_shared, cad_update_shared and cad_revoke_shared, though those distinctions are left implicit rather than named.

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?

No when-to-use guidance, no prerequisites (e.g. must a drawing be open/saved first), and no mention of when to prefer cad_update_shared or cad_revoke_shared. The phrase 'current drawing' faintly implies context but gives the agent nothing actionable about alternatives.

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