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

Despite annotations already marking the tool as read-only/idempotent/non-destructive, the description goes well beyond: mentions no API key required, the embedding limitation ('only items whose full text ships are embedded at all'), the PCA variance caveat, and payload scaling behavior. This is rich, non-obvious 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?

Despite being longer than typical, every sentence earns its place: purpose, interpretation caveat, methodology distinction, auth, data availability, payload scaling, and practical advice. Front-loaded with the core function, then organized caveats. No redundancy.

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?

Output schema exists, so return values need no explanation. The description covers the tool's purpose, usage caveats, auth requirements, data limitations, scaling behavior, and interpretation warnings. Very complete for a tool with 9 optional parameters and a visualization output.

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 baseline is 3. The description adds meaningful value for the 'limit' parameter by explaining its scaling impact and advising to keep it low for text-only clients, going beyond the schema's 'Items projected (default 300, max 2000)'.

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 opens with a specific verb and resource: 'A 2-D scatter of a filtered set, projected from the stored 768-dimension embeddings by PCA.' It clearly distinguishes the tool from siblings by noting 'This is PCA, not UMAP' and explicitly contrasts it with 'semantic landscapes on islam.zmo.de.'

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?

Provides solid usage context: instructs to read 'explained_variance' before drawing conclusions, warns that the payload scales with limit, and advises text-only clients to focus on the variance summary rather than coordinates. Does not explicitly name sibling alternatives like get_similar_items, but gives clear contextual guidance.

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