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

Adds behavior the annotations do not cover: the note is private to the user, the other party is not notified, and nothing is sent — a crucial fact for an agent deciding whether this is safe to call on the user's behalf. It also explains the pointer-not-copy storage model. It misses the idempotency implication (idempotentHint=true means re-tracking the same line is harmless) and says nothing about how a tracked line is later cleared.

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 is front-loaded in the first clause, then privacy and the sibling pointer follow in a sensible order. The clause 'so the words stay where they were said' is evocative but slightly padded; otherwise every sentence carries information the agent needs.

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 write tool with full schema coverage and no output schema, the description covers what it does, who sees it, and how it differs from whats_new. What is missing is lifecycle context: how a tracked line is removed or resolved later, and whether re-tracking the same line duplicates a note.

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 schema already documents kind, index, due, owedBy and packageId, including 'Use 0 for an ask.' The description adds only the conceptual framing that it points at a line rather than copying it, which mildly informs the index parameter but gives no new syntax or constraint detail. Baseline 3 applies when the schema does the heavy lifting.

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?

Names a specific verb and resource ('Mark one line of a package') and enumerates the supported kinds (open question, decision to revisit, the package's own ask). It also distinguishes itself from the sibling whats_new, which lists rather than marks outstanding items, so an agent can route correctly without opening a 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?

Gives a concrete trigger: 'Call it when the user says they are waiting on something or want to come back to it,' and contrasts it with whats_new for listing. It stops short of naming exclusions such as remind_me (time-based reminders) or resolve_item (clearing a tracked line), so the boundary with those siblings is left implicit.

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