perseus_focus

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

Annotations set destructiveHint=true, and the description adds eviction behavior ('lowest-salience non-pinned items are evicted when it overflows'), default capacity (32), and pinning semantics, providing rich behavioral context.

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?

The description is dense and front-loaded with the core concept, but it is slightly long. Every sentence adds value, though it could be more concise without losing meaning.

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?

Given 8 parameters and no output schema, the description covers the workspace model, capacity, eviction, and pinning. It distinguishes from memory tools but omits details on some operations (e.g., drop, clear) which are left to 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?

With 100% schema description coverage, each parameter is already explained in the schema. The description adds general workspace behavior but does not significantly elaborate on individual parameter usage beyond what the schema provides.

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 clearly states the tool is a bounded, salience-ranked workspace. It specifies the verb 'renders' for no args and 'add/pin admit items', and explicitly distinguishes from long-term memory tools like @mimir/@memory.

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 states when to use (no args for viewing, add/pin for insertion) and contrasts with alternatives: 'Distinct from long-term recall... bounded and actively maintained, not unbounded memory.'

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