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

Annotations only give readOnlyHint=false and idempotentHint=false; the description adds substantial value beyond that: default-off behavior, persistence across updates and URL resets, workspace-level precedence, future-visits-only scoping, input masking, background pausing, 8 MB/visit and 1 GB/workspace caps, and 30-day retention. This is exactly the operational context an agent needs for a mutation toggle.

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?

Front-loaded with the core action, then layered with the constraints that matter. Dense and mostly waste-free, though the trailing list of limits and unaffected features packs a lot into long clauses.

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?

With no output schema and thin annotations, the description covers behavior, limits, retention, and interactions thoroughly for a 2-param toggle. The remaining gap is authorization/permission requirements and an explicit statement of what proposal_id identifies.

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% for two parameters (proposal_id, on), so the description carries the burden. 'Through this page's link' loosely maps proposal_id to a page and 'turn it on' implies the boolean, but neither parameter is named or explained, leaving the mapping to inference.

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 pair (enable/disable) plus the exact resource (HTML session recording) and its scope (this page's link and folder visits). An agent can immediately tell it is the per-page replay toggle, distinct from get_replay_settings and set_replay_settings.

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?

Conveys the default state ('Off by default — recording starts only after you turn it on') and precedence ('workspace-wide off switch takes precedence'), which implies when toggling is meaningful, but it never explicitly routes the agent between this tool and the sibling get_replay_settings/set_replay_settings.

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