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

Annotations cover the safety profile (readOnly=false, idempotent=false, destructive=false), so the bar is lower. The description goes beyond them with two genuinely useful behavioral facts: writes are partial ('Only the fields you pass change') and renaming does NOT cascade to `[Name]` references. Auth requirements and error behavior remain undisclosed, keeping it at a 4 rather than 5.

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 tight sentences, front-loaded with the core action, then the partial-update rule, then the caveat. No filler; every sentence carries information an agent needs before calling.

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 30-parameter mutation tool with no output schema and sparse param descriptions, the description is thin — it covers the partial-update contract and the reference-rewrite gotcha but nothing about field semantics or valid combinations. The rich nested $defs (ScaleSchema, ConditionSchema) compensate somewhat, but the definition is still incomplete for this complexity.

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 7% (just block_id and project_id), so the schema does not carry the load for the 28 undocumented fields. The description adds one high-value semantic that spans all parameters — partial-update behavior — but leaves the meaning and valid values of the remaining fields unexplained.

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 one block in place' — which is unambiguous against add_block and delete_block. It does not explicitly name or differentiate itself from siblings, but the singular 'one block, in place' framing is clear enough for selection.

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 description routes the agent to validate_script after edits and implies partial-update usage, but never says when to choose update_block over add_block or how it interacts with get_script. Usage is implied rather than stated.

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