review_model

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

With no annotations, the description carries the behavioral burden itself: it discloses that the tool returns 'prioritised concrete fixes' and enumerates the scoring dimensions, which tells the agent what to expect. It does not explicitly state that it is non-mutating, but 'critique' strongly implies a read-only analysis, and the output nature is well described.

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?

Two sentences, front-loaded with the core action followed by the trigger condition. The dimension list is dense but each item is a distinct scoring criterion, so it earns its length; nothing is redundant.

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 read-only review tool with a fully documented two-parameter schema and no output schema, the description adequately covers purpose, output ('prioritised concrete fixes'), and usage timing. Only the precise return format/prioritisation logic is left unstated, which is a minor gap.

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 100%, with the 'purpose' enum fully documented in the schema (hero/prop/background/game). The description adds no further semantics about 'objects' or 'purpose' beyond what the schema already provides, so the baseline 3 applies.

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?

The description states a specific verb ('critique'/'scores') and resource (a model), and enumerates the dimensions assessed (edges, silhouette, weathering, integrity, presentation). It is clear what the tool does, but it never distinguishes itself from near-siblings like analyze_quality or compare_reference, which could plausibly cover overlapping ground.

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?

'Run it before declaring a model finished and work down the list' gives an explicit when-to-use condition and workflow. It does not name alternatives or when-not to use it (e.g., versus analyze_quality), so it falls short of full routing guidance.

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