goldhold_focus

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

With no annotations, the description carries the full burden, and it does disclose a significant behavioral trait beyond the schema: 'Also creates ASSET_REF records for each ref.' This is valuable and non-obvious. It does not, however, state whether the call overwrites the existing focus manifest, what happens to previous refs, or what the response contains.

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 two tight sentences. The core action is front-loaded, the scope is defined with a compact hyphenated list, and the side effect is placed second. Every word earns its place with no filler or repetition.

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?

The tool mutates a persistent state and creates records, so an agent would benefit from knowing whether the focus is replaced or merged and whether the side effect is reversible. The description explains the side effect but omits overwrite semantics and return behavior. Given no output schema and no annotations, this is a noticeable gap, though the flat parameter set keeps it from being severe.

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 baseline is 3. The description adds only conceptual mapping: 'what matters now' maps to priorities and 'what to ignore' maps to ignore. It does not add syntactic detail, type constraints, or behavior beyond the schema, so it meets but does not exceed the baseline.

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 names a specific verb and resource: 'Set the current focus manifest' and then enumerates what the manifest contains ('what project is active, what matters now, what to ignore'). It also distinguishes itself from sibling tools by focusing on the concept of 'focus' and adding the unique side effect of creating ASSET_REF records. This is a clear, non-tautological statement of purpose.

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 implies a clear context: use this tool whenever the agent needs to establish or update the current focus manifest. However, it gives no explicit guidance about when not to use it or which sibling tools might be appropriate alternatives. The context is reasonably inferable but no exclusions or comparisons are offered.

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