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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is covered. The description usefully discloses the upsert trait (it may create a concept, not just link one), but omits what happens on key/type conflicts, whether re-assignment is idempotent, and what creation side effects occur (asil/phase/title application).

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?

A single front-loaded sentence with parallel structure describing the two modes and no filler. It is efficient, though arguably too sparse for a six-parameter mutation tool with four creation-only parameters.

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?

The core branching logic is conveyed, but for a non-read-only tool with six parameters and no output schema, the definition leaves creation-only parameters (asil, phase, title) unexplained in context and says nothing about the result of the call or failure modes.

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 schema itself already says type is 'required when the key is new', so the description largely restates that relationship. It does add the key/type interplay framing, but says nothing about the optional asil, phase, and title parameters, which are only meaningful on the creation path.

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 ('Assign an existing concept') and clearly distinguishes the two modes: attach-by-key versus create-and-attach. It does not name siblings like create_concept or get_work_item_concepts, so an agent must infer the boundary from context.

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 clause 'when a type is supplied' gives a usable trigger for the create path, which is genuine usage guidance. However, there is no when-not guidance (e.g., use create_concept directly for a standalone concept, or get_work_item_concepts to check existing links) and no mention of error behavior if the key already exists.

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