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

Annotations only say it is a non-read-only, idempotent, non-destructive write. The description goes well beyond that: create-or-update semantics for positive minutes, deletion semantics for 0, explicit refusal to merge multi-entry days, partial-failure reporting, and the note being applied to every written day. That is exactly the extra side-effect detail annotations cannot convey.

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?

Three sentences, no filler, front-loaded with the scope ('up to 31 days') and then the write/clear rule and the skip rule. Every clause carries actionable information.

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?

An output schema exists, so return formatting need not be explained, and the description already covers the mutation semantics, skip behavior, and reporting of skipped days. Nothing material is missing for correct invocation.

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 baseline is 3, but the description adds real meaning: the meaning of minutes=0 (clears the day) versus >0 (create/update), which is only implied by the schema's minimum of 0, and the fact that note is broadcast to every day written.

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 (set), resource (one project's total minutes), and bound (up to 31 days) in the first clause. The behavior 'more than 0 creates or updates that day's single entry, 0 clears it' distinguishes it from additive siblings like log_time and log_time_on_days without needing to open their schemas.

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 clear context for when a day is written versus skipped: days holding several entries or a running timer are skipped and reported rather than merged. It does not name an explicit alternative tool for those skipped cases (e.g. update_entry, merge_entries), so the when-not path is described but not routed.

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