tag_analysis

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

No annotations, so the description must carry the full burden. It discloses a key behavioral trait: returns empty for untagged databases. It also explains the OPEN-database side effect (webUrl to docusky.org.tw, rendered in MCP Apps-capable hosts). It does not discuss read-only nature, permissions, or rate limits, but 'Summarize' implies a read 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 core purpose, followed by meaningful preconditions and the OPEN/webUrl caveat, then an Args block. Efficient overall, though the webUrl/MCP Apps aside could be trimmed for some hosts.

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 description covers purpose, preconditions, side effects, and parameter semantics, which is substantial for a 5-param tool with 0% schema coverage. An output schema exists, so return-value details are not required. It could go slightly further on parameter usage (owner_username conditions) and target semantics, but is largely 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 coverage is 0%, so the description must document all 5 params — and it mostly does: db, query (with '.all' sentinel), corpus ('[ALL]' sentinel), target ('OPEN'/'USER'), and owner_username ('when applicable'). The sentinel values and enum-like values for target are essential semantics the bare schema lacks. Minor gap: no guidance on when owner_username applies beyond 'friend-shared database'.

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 (Summarize) and resource (DocuXML tags: people, places, dates, custom markup), scoped to a query's hits. The parenthetical enumeration of tag types makes the resource concrete and distinguishable from sibling analysis tools like word_cloud or twodim_analysis.

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 it is meaningful ('only meaningful for databases whose documents carry inline tagging') and what happens otherwise ('returns an empty result otherwise') — a clear precondition. However, it doesn't compare itself to sibling analysis tools (word_cloud, twodim_analysis), leaving the agent to infer which analysis tool to pick.

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