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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds genuinely new behavior: it names the returned fields and states that rate is frozen on the entry so later rate changes never move it — a non-obvious immutability guarantee. It stops short of covering duplicate/repeat-call behavior or error cases (e.g. ambiguous project match).

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?

Two tight sentences: the effect and return values come first, then the input shape and rate semantics. Every clause carries information that is not already in the schema or annotations.

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 10-parameter mutation tool with no output schema, the description covers the effect, the returned fields, the duration-vs-end rule and rate immutability. Missing only edge behavior such as what happens when the project match is ambiguous or when a timer is already running.

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 already 100%, so the baseline is 3, and the description earns above that by clarifying the either/or input rule ('start plus end or minutes') across parameters and by pinning down that rate is hourly in MAJOR units — a format fact the schema only hints at with '90 euros an hour'.

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?

The description uses a specific verb+resource ('Log time already worked as one entry') and even states the return values (id, duration, amount). It does not differentiate itself from the similar sibling 'entry_log', so an agent cannot tell from the text alone which of the two to pick.

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?

'Log time already worked' implies past/retroactive time rather than a running timer, which implicitly points away from timer_start/timer_stop, and 'Give start plus end or minutes' scopes the input shapes. However, no sibling is named and there is no explicit when-not guidance (e.g. use entry_edit to correct an existing entry, entry_log vs entry_add).

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