Update daily log

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

Annotations cover the safety profile, and the description adds real behavior on top: patch semantics (only passed fields change), replace-not-append for text, materials_delivered overwriting material notes, inability to clear delay/visitor markers, immutability of date and project, and no client/crew notification. That is far more than the annotations convey. One mild tension: 'replaces only the fields you pass' reads as idempotent while idempotentHint=false, but this is not a direct contradiction.

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?

Front-loaded with the purpose, then ordered from semantics to side effects. Every sentence carries information (patch behavior, read-first caveat, field limitations, immutability, no-notification), though the delay/visitor sentence is dense and slightly repetitive with the materials sentence.

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 11 parameters, no output schema, and a mutation, this description does what is needed: it explains patch semantics, the return shape ('as get_daily_log shows it'), the fields that cannot be modified, and the notification side effect. An agent has enough to invoke it safely without further probing.

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 baseline is 3; the description still adds genuine semantics beyond the schema — replacement vs. append on text fields, that materials_delivered overwrites material notes, and that weather_delay/schedule_delay/visitors can only set, not clear. These are behaviors an agent cannot infer from the property descriptions.

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 (change/update) and resource (daily log) plus the exact field families it touches. It differentiates itself by reference to siblings: results match 'get_daily_log' and the id comes from 'list_daily_logs', so an agent can place it among the create/get/list daily-log tools without opening 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 actionable preconditions: 'read the log first to add to its notes' and 'the log reaches no client or crew, so this tool runs without asking'. It clearly bounds what the tool is not (date/project immutable, delays can't be cleared), but it never explicitly names update vs. create_daily_log as the alternative for a given situation.

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