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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered; the description still adds real substance by disclosing that weekly_hours replaces the entire week, that changing slug leaves the old address working, and that promotion to main page is out of scope. It stops short of stating whether permission requirements, validation failure behaviour, or partial-update semantics apply when a single field is invalid.

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?

Purpose and the top-level editable fields are front-loaded, then the parameter rules, then the card-draft routing rule. It is dense but nearly every clause carries operational meaning; only the repeated framing around cards ('that card saves to the existing page with Save changes') could be tightened.

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?

A 14-parameter mutation with an output schema and full annotations is largely covered: editable fields, enum semantics, time formats and the draft-first workflow are all explained. The workspace_id, conversation_id and idempotency_key semantics are left entirely to their schema descriptions, which is acceptable but means the description is not self-sufficient for the multi-workspace case.

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 only 36% schema description coverage, the description compensates heavily: primary_color must be #RRGGBB, calendar_view takes month (default) or two_weeks, theme takes dark (default) or light, weekly_hours takes entries of days (1=Monday..7=Sunday) with start/end as HH:MM, days sharing hours collapse into one entry, a break splits a day into two entries, and a missing end defaults to 18:00. These are semantic rules the JSON schema's regexes alone cannot convey.

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?

Opens with a specific verb and resource ('Change one booking page') and enumerates exactly which attributes are editable: title, meeting length, color, location, weekly hours, address, description, calendar view and theme. This clearly separates it from well_create_booking_page and well_delete_booking_page, and the 'never makes another page the main page' clause rules out a plausible misreading.

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 explicit routing rule: on a chat that can draw cards, call well_get_booking_page_draft first on every edit ask, and call this tool only when card_drawn is false or the user asks to change it now. It also names the alternative (the card's 'Save changes' flow) and warns not to tell the user to press 'Create page' for an existing page.

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