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

The annotations only declare readOnlyHint=false and destructiveHint=false, but the description goes much further: it says the call is PROPOSED and never performed directly, returns status='confirmation_required' with an action_id and plan_token, and that the write only happens via confirm_action. That is a concrete disclosure of the two-phase side effect that the annotations cannot convey. It does not cover failure modes or whether a proposal expires, which keeps it off a 5.

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?

The payload variants are packed into a single semi-colon-delimited sentence, front-loaded before the confirmation rules, with no filler. The shorthand ('number: value', 'line_id + value') is dense but readable, though a slightly cleaner formatting of the type table would help scanning.

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, the description wisely documents the return shape (status='confirmation_required', action_id, plan_token) and the confirmation handoff, which is the critical unknown for this tool. The remaining hole is the unexplained required item_id and what a 'fact' attaches to when multiple key results exist on a goal.

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 only 17% (of 6 params), so the description must compensate, and it does for value ('the new total so far'), line_id, status enums (yes|partial|no vs done|not_done), and comment, all mapped to the key-result type that requires them. The gap is item_id, which is required but never explained in either the description or the schema, leaving its meaning ambiguous.

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 and resource ('Record a fact for one key result of a goal') and immediately disambiguates it from the goal-reading siblings by describing the write and its effect ('Lands on the goal's progress chart'). The per-type payload breakdown (number / composition / budget / named_list / event) makes the resource granularity unmistakable.

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?

It tells the agent which parameters to supply for each key-result type, which is effectively the when-to-use rule set, and it names the follow-up step ('the write happens only after confirm_action'). It stops short of explicitly naming an alternative tool or stating when not to use this one, so it is clear context without exclusions.

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