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

Annotations declare destructiveHint=true and openWorldHint=true, but the description carries far more: it discloses the two-step confirm/accept flow, that credentials (database password, file storage key, open-models key) are rotated while user-set secrets move unchanged, that the sending domain's link forwards for 30 days then stops, and that the owner's agents lose access. It also clarifies the immediate call only drafts an offer, which reconciles the 'moves nothing' framing with the eventual ownership change rather than contradicting the destructive annotation.

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?

Content is front-loaded with purpose and immediate action before consequences and parameters, and virtually every clause carries operational information. The main weakness is that it is one dense block of prose rather than segmented sentences or bullets, which makes the credential-rotation and link-expiry details harder to scan.

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 non-idempotent, destructive, open-world mutation with an output schema, the description supplies everything an agent needs: pre-call permissions context, the multi-party acceptance flow, what changes (owner, credentials), what persists (data, database, files, settings), and what to surface to the user (confirm_url, two remaining steps). Nothing material is left to inference.

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 real meaning beyond the schema: keep_access is framed as 'keep opening the app afterwards' (vs. the schema's 'share list'), cancel is scoped to 'only to withdraw an offer the user no longer wants', and to_email is tied to the receiver accepting signed in with it. The only minor gap is that project_id is never elaborated, which is acceptable given its obvious role.

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?

The opening clause names a concrete verb and resource ('Hand a spawnpoint project to another person's spawnpoint account') and adds a use-case example (a client at end of engagement). It is clearly distinguishable from siblings like share_project or terminate_project because it specifies a change of ownership, not access-granting or deletion.

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?

It gives an explicit trigger ('When the user asks for that, call this tool right away'), explicitly removes a hesitation ('there is nothing to ask first'), and describes what to tell the user afterwards. It also routes the cancel case ('get_project shows an open one as account_transfer') and conditions keep_access on wanting continued access. This covers when-to-use, when-not-to-hesitate, and the sibling cross-reference.

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