Log Event (calendar write)

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description goes well beyond by disclosing the write path (public.events, optional event_people/shared_events, then rebuilds life_state), auth requirements (API key or OAuth with scope context; share tokens cannot write), idempotency semantics, that unknown people names do not fail the write, that public events return a share_url, and the $0.10 cost.

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 and exclusions are correctly front-loaded, and the two examples earn their place by showing the anyOf date/alias split concretely. However, the mid-paragraph inventory of optional fields (end_date, end_time, location/city+country, description, category, external_url, visibility, image_url, timezone, date_precision, share_with, people, idempotency_key) largely restates a schema that is already 100% documented, making the block longer than it needs to be.

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 mutation tool with an output schema and full annotation coverage, everything an agent needs is present: required fields and their alias forms, auth and cost constraints, idempotency behavior, side effects on downstream state (event_people, shared_events, life_state rebuild), and the public-visibility return value.

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 description coverage is 100%, so the schema already documents the parameters and the baseline would be 3. The description still adds meaning beyond it: soft dates expand to first-of-period and set metadata.date_precision (day|month|year|approx), accepted time formats, alias pairs, and a worked example call for each of the two anyOf branches.

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 ('MUTATES the authenticated user calendar') and immediately carves out its domain: non-food days such as funeral, cremation, appointment, dinner. It is clearly distinguishable from log_food, log_travel, and log_transaction, which it names outright.

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?

Explicit when-to-use ('non-food days'), explicit when-not-to-use ('anything that is not a food log', 'Do not store this as a chat memory'), and explicit alternatives ('For trips/residences prefer log_travel', 'Prefer log_transaction / import_venmo_gmail for cashflow-first digs'). Nothing about routing is left to inference.

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