Update the engagement

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

With no annotations, the description carries the transparency burden and does meaningful work: it discloses partial-update semantics (unspecified entries are left alone), the upsert rule (id = update, omit = add), the provenance requirement (source and confidence on every entry), and a response contract (the response reports how many entries still have no source). It also documents the convention for confidence='inferred'. Minor gaps remain around error handling for nonexistent ids and authorization, but the core mutation behavior is well disclosed.

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 description is front-loaded with the core action and scope, then flows logically through the upsert rule, provenance fields, response behavior, and the inferred-source convention. The bilingual format doubles length, but that matches the tool's ja/en/both lang parameter, and every clause earns its place.

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 tool this complex — 15 parameters with seven nested object types, no annotations, and no output schema — the description covers the essential behavioral contract: partial update semantics, upsert pattern, provenance requirements, and the key response behavior. It doesn't document error cases, authorization, or whether supplied ids must already exist, but those are reasonable omissions against how much the description does convey.

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 33%, so the description must compensate — and it does. Rather than enumerating each of the 15 parameters, it explains the cross-cutting semantics that apply to all array-entry types: supply an id to update, omit it to create; each entry can carry source and confidence; the confidence values are enumerated with their meaning; and the response reports the count of unsourced entries. This adds meaning the per-field schema descriptions cannot convey.

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 states a specific verb and resource ('Partially update the engagement') and enumerates exactly what can be changed: phase statuses and add/update of risks, decisions, actions, stakeholders, deliverables, and notes. This clearly separates it from siblings such as create_engagement, get_engagement, archive_engagement, and delete_engagement.

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?

The description makes the tool's scope clear — any partial modification of an existing engagement — so the intended use is implied. However, it never explicitly names alternatives or states when not to use it (e.g., when to prefer create_engagement or delete_engagement), so routing to this tool is left to inference from the sibling names.

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