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

Discloses a high-value trait the annotations don't cover: the raw access token is returned only once and cannot be re-read, warning the agent to surface it immediately. It also explains retry/dedup semantics via idempotency_key; note the mild tension with idempotentHint=false, though keyed dedup is a distinct concept and not a true contradiction.

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?

Three tight sentences: purpose first, then the critical token-once warning, then retry behavior. No filler, and the most operationally important detail (token shown once) is front-loaded.

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 exists, and the description covers the one return value that matters (the one-time raw token). Annotations already carry the safety profile (destructiveHint=false, openWorldHint=true). It stops short of describing the portal URL or link metadata, a minor gap.

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?

With 75% schema coverage, most params (label, expires_at, client_email, workspace_id) are already documented in the schema, so the baseline is 3. The description adds genuine meaning for idempotency_key — that a repeat call with the same key returns the original result — which the schema itself does not explain.

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+resource ("Create a magic-link review portal") and adds scope ("where a client reviews workspace content without an Aidelly account"), which cleanly distinguishes it from the many sibling create_*_link tools (report_link, connect_link, short_link). An agent can select it without opening the 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?

The description conveys the intended context (client review without an account) but never names alternatives or a when-not condition, e.g. pointing to aidelly_revoke_client_review_link for cleanup or aidelly_list_client_review_links for retrieval. Usage is implied rather than stated.

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