Remove sources from graph

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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description adds the details that matter: the Tableau content is preserved, context attached to removed nodes may be lost while graph-wide context survives, unknown LUIDs are reported and skipped rather than erroring, and the underlying web-app API is undocumented and may change. That is meaningful behavior beyond the structured hints.

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 'WRITE:' marker and the core action, then broken into short blocks covering scope, parameters, constraints, return/rollback, and API risk. No sentence is filler; each adds a distinct operational fact.

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?

For a destructive graph mutation, everything an agent needs is present: required id, LUID provenance, skip behavior for missing nodes, user confirmation, reversibility via add_sources, and the instability caveat. An output schema exists, and the description still summarizes the return value, so nothing material is missing.

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 0%, so the description carries the full burden and mostly delivers: it explains where LUIDs come from, that either list accepts either type because the type is resolved from the graph, and that graph_id is required or falls back to TABLEAU_KNOWLEDGE_GRAPH_ID. Slight mismatch with the schema (no required params, all nullable) is not resolved explicitly, keeping it from a 5.

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?

Opens with a specific verb and resource ('WRITE: remove published data sources and/or workbooks, and the nodes built from them, from a knowledge graph') and immediately clarifies scope with 'The Tableau content itself is untouched.' An agent can distinguish this from add_sources or delete_semantic_context without opening any schema.

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?

Gives concrete preconditions ('Exact LUIDs only (a source's properties.luid from list_sources)', 'Confirm with the user first') and names the inverse operation ('add_sources with the same LUIDs puts it back'). It does not explicitly contrast with other removal-style siblings, but the LUID-sourcing pointer effectively routes the agent to the right upstream tool.

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