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

Annotations declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is already covered. The description adds non-trivial mutation semantics: silent field retention on omission, and that 'story_ids' replaces rather than appends to linked stories — important because that call can silently drop existing links. It stops short of mentioning permission/auth needs.

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?

Three short sentences, zero filler, with the identifier requirement and the partial-update rule front-loaded before the destructive-replace caveat. Every sentence 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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. The description supplies the two behavioral quirks an agent most needs (omission semantics, replace-not-append), leaving only minor gaps such as required project scoping and permissions.

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% and the nested 'stakeholder' property already carries nearly identical text ('Omit a field to leave it unchanged. story_ids replaces the linked stories...'), so the description largely restates structured data. Baseline 3 is correct when the schema does the heavy lifting.

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 ('Update a stakeholder by UUID'), which cleanly separates it from siblings stakeholders_create, stakeholders_get, and stakeholders_delete. It does not explicitly contrast itself with update-adjacent alternatives like projects_align_stakeholders_to_stories, but the name/resource pairing is unambiguous.

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?

'Omit a field to leave it unchanged' tells the agent how to perform a partial update, which is genuinely useful invocation guidance. However, there is no explicit when-to-use/when-not guidance versus stakeholders_create or the alignment tools, so usage is only implied.

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