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

Annotations already flag this as a non-read-only, non-destructive, open-world mutation, so the description could have added value by explaining what 'read' actually changes (unread counter, stats, notifications). Instead the single sentence restates the name and the parameter's provenance, adding essentially no behavioral context.

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?

One short, front-loaded sentence with no filler. It is efficient, though its brevity is the reason behavioral detail is missing rather than a sign of tight editing.

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 one-parameter state-change tool with annotations present and no output schema, the definition is minimally sufficient: the agent knows which id to pass and where it comes from. It leaves the effect of the mutation and any re-call behavior unexplained.

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% and the schema itself says 'Id from list_leads,' which is exactly what the description says. The description adds no format, range, or error semantics beyond the schema, so 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?

Specific verb ('Marks ... as read') plus a specific resource ('a lead'), which cleanly separates it from the read-marking siblings mark_chat_read, mark_notification_read, and mark_notifications_read. It also names the source list (list_leads), so the agent knows the lead must be one already retrieved.

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?

Usage is only implied: the phrase 'from list_leads' hints that the prerequisite is a prior list_leads (or get_lead) call, but there is no explicit when-to-use, no note on idempotency, and no mention of whether read state affects get_leads_stats or lead unread counts.

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