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

Goes well beyond annotations: partial-update semantics ('Only the fields provided change'), the destructive whole-block replacement of kindMetadata with `{}` = clear, the immutability of id/parent, the fact that auto_layout_mcd can overwrite a hand-set position, and that a rename does not rename the SQL table. It also discloses the failure mode (error, nothing written), matching destructiveHint=true without contradicting it.

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?

Front-loaded with what the tool owns before the exception rules, then exclusions, then refusals, then sibling routing. Dense but every sentence carries non-redundant information; there is no filler or restatement of the title.

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 10-parameter mutation tool with a nested object, no output schema, and destructive semantics, the description supplies the merge rules, side effects, immutability constraints, and error behavior an agent needs to call it safely. The only uncovered parameter, expectedProjectId, is fully documented in the schema.

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 baseline is 3; the description earns an extra point by stating the cross-cutting merge-vs-replace rule across parameters (partial update except kindMetadata) and the x/y-absent auto-layout consequence. Some content (kindMetadata replacement, rename/table-name caveat) duplicates the schema's own descriptions, and expectedProjectId is left 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?

Opens with a specific verb+resource and scope ('Modifies one existing ERD entity (kind='entity')') and enumerates exactly which fields it owns. It explicitly hands off columns to update_field/add_field and relations to update_relation, so the agent can distinguish it from the ~150 siblings without opening a 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?

States when to use it, when NOT to (columns, relations, creation, deletion go to named siblings), and the refusal conditions ('REFUSED with an error, nothing written, on an unknown id or a block that is not an ERD entity'). Alternative tools are named rather than implied.

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