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

The annotation readOnlyHint=false already flags mutation, so the description earns credit by adding behavioral detail beyond it: the operation is an upsert, the key is auto-detected from MCP headers rather than user-supplied, and updates are partial ('Only the fields you pass are changed; omit a field to leave it untouched'). This does not contradict the annotation. It omits the return value and failure behavior, but the mutation semantics are well covered.

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 sentences, each with a distinct job: when to use, what it does plus how keying works, and the partial-update rule. The 'WHEN:' prefix front-loads the most decision-relevant information, and no sentence repeats schema or annotation content.

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 simple 4-parameter upsert with no output schema, the description resolves the critical unknowns: the trigger condition, the auto-detected keying behavior, and merge semantics. The one meaningful gap is that it never states what the tool returns after saving, which matters more here because no output schema exists to fill that in.

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 the schema already documents all four parameters with format examples (e.g., '"10.0.2645.32"') and domain context for customModelIds (extensions plus ISV models). The description adds the useful clarification that the profile key is not a parameter and that omitted fields stay untouched, but that is upsert/merge semantics rather than per-parameter meaning, so the baseline of 3 is appropriate.

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 ('Creates or updates a Client Profile') plus the exact scope (keyed by the current caller's ADO org/project), and explicitly differentiates itself from its sibling resolve_client_profile by naming the condition that triggers it. An agent can distinguish this from the ~90 sibling tools without opening the schema.

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?

Opens with an explicit WHEN clause ('no profile was found by resolve_client_profile and the user wants one created (or updated)') that names the alternative tool and the condition selecting between them. It also explains the downstream benefit ('future release-note requests never need v1/v2/customModelIds again'), which clarifies why the agent should persist this data.

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