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

The annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=false, so the safety profile is carried structurally. The description adds genuinely useful partial-update semantics ('Only the fields given change'), which is not in the schema or annotations, but it does nothing to explain the destructiveHint flag (what is lost when status flips to cancelled, whether prior values are recoverable) or any permission requirements.

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 short sentences, zero filler, with the affected fields front-loaded and the partial-update guarantee appended where it matters most. Nothing is repeated from the schema beyond the enum/range values, which serve a semantic purpose.

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 flat five-parameter mutation with no output schema, the description covers every writable field and the update semantics. It stops short of explaining error behavior, whether changes are recorded in list_org_goal_updates, or why the tool is flagged destructive, which is the remaining gap.

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 only 20% (goal_id alone is documented), so the description must compensate, and it does: it enumerates the four writable fields, spells out the status enum values, and gives the 0-100 range for progress. The only shortfall is that it never states that goal_id is the sole required parameter or where it comes from, leaving that entirely to the schema.

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 (change) and resource (company-wide goal) plus the exact mutable fields, which implicitly separates it from create_org_goal, list_org_goals, and update_agent_goal. The 'company-wide' qualifier is doing real disambiguation work against the agent-goal siblings, though no sibling is named 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?

Usage is only implied: an agent can infer 'use this to modify an existing goal,' but there is no explicit when-to-use/when-not, no pointer to list_org_goals for obtaining the id (that lives only in the schema), and no mention of create_org_goal as the alternative for new goals.

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