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

Beyond the readOnlyHint annotation, it discloses rich behavioral detail: contentOverflow is a light counter, field-absent means no card exceeds the cap and explicitly 'does not mean I did not look,' linkedProjects is at any depth vs rootCells stopping at direct children, and that access/pin are not resolved here. The expectedProjectId refusal behavior is also surfaced.

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?

It is front-loaded with the main return contents, which is good, but the prose is dense and rambling with heavy em-dash nesting and long run-on sentences. Most sentences carry real information, but the structure is not tight and could be considerably trimmed.

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?

With no output schema, the description does the heavy lifting by explaining the return fields (contentOverflow, linkedProjects) and their absence semantics in detail. The top-level 'blocks, people, dependencies' structure is only named, not described, leaving 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%, so the schema already documents both parameters (including the refusal semantics for expectedProjectId). The description adds no syntax or meaning beyond what the schema 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 and resource ('Returns an overview of the schema') and enumerates the concrete outputs (blocks, people, dependencies, root blocks with direct children). It distinguishes itself from siblings by contrasting its light counter with analyze_canvas's detailed list and its 'points to' semantics with get_linked_project's reachability check.

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?

It routes the agent to alternatives under explicit conditions: 'for the detailed list... see analyze_canvas' and 'to actually read a target... see get_linked_project.' It also hints at timing ('read at the start of a turn'). It does not state when to prefer this over other overview-ish siblings like get_full_data, so no explicit when-not.

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