Add sources to graph

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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) it discloses that ingestion is asynchronous and takes seconds to minutes, that the operation is additive only, that re-adding re-ingests, and that it relies on an undocumented web-app API that can change without notice. Note the 're-adding re-ingests it' wording is consistent with idempotentHint=true (end state unchanged), not contradictory.

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-loads the WRITE label and the core action, then layers constraints in short, scannable paragraphs with zero filler. Slightly dense with stacked parentheticals (env var name, ingest.status, site_search example), but each sentence carries actionable information.

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 three-parameter mutation tool with 0% schema coverage, the description covers what is added, requiredness of graph_id, LUID format and discovery, the async verification loop, and API stability risk; an output schema exists so return values need no explanation. Only error behavior for invalid LUIDs is unstated, which is minor.

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%, but the description explains all three parameters: what pds_luids and workbook_luids mean, that they must be exact LUIDs rather than names, how to discover them, and that graph_id is required with an environment-variable fallback and no primary-graph default. This fully compensates for the bare schema.

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 an explicit 'WRITE:' marker and a specific verb+resource: add published data sources (pds_luids) and/or workbooks (workbook_luids) to a knowledge graph. An agent can distinguish this from remove_sources and list_sources without inspecting 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 explicit routing ('find them with list_sources(site_search="part of a name")'), an explicit verification path ('check with list_sources (ingest.status)'), a prerequisite ('graph_id is required (or TABLEAU_KNOWLEDGE_GRAPH_ID): this never falls back to the primary graph'), and a workflow constraint ('Confirm the list with the user first').

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