scan_primary_assets

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description gets credit for what it adds: synchronous execution, the 'rules without paths are skipped' edge case, and the shape of the result. The one thing not addressed is that a rescan mutates the in-memory Asset Manager registry despite readOnlyHint=true, which is worth flagging contextually but is not a contradiction given the idempotent/reindex nature of the operation.

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 the primary action and compact overall, but the return value is described twice — once inline ('Returns num_assets_found, types_scanned and per-type scanned_types') and again as a full 'Returns: {...}' block with a partly different field list. One of those sentences is largely 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?

With no output schema, describing the return object is genuinely necessary and it is done here, along with preconditions and scoping/skip behavior. Minor gaps remain, such as how per-rule failures are surfaced, but for a single-optional-parameter read tool the picture is close to complete.

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 fully documents primary_asset_type, including the empty/unknown-name behavior. The description only restates '(or only primary_asset_type)' without adding syntax or format detail, so the baseline of 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?

States a specific verb ('Synchronously rescan') and resource ('directories and specific assets of every PrimaryAssetTypesToScan rule'), plus the resulting effect ('so the Asset Manager registers their primary assets'). This is clearly distinguishable from the neighboring rule-management siblings such as add_primary_asset_rule and get_primary_asset_types.

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?

Explicitly names the sequencing condition: 'Run it after add_primary_asset_rule.' It also clarifies scoping behavior when the optional parameter is omitted versus set. It stops short of naming an explicit when-not-to-use or an alternative tool, so it falls just shy of a 5.

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