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

Annotations already declare destructiveHint=true, so the description doesn't need to repeat that. It adds valuable behavioral context: the bind 'VERIFIES the live mapping materialized' and 'nothing goes in the bundle', plus the note that bound live schemas are accessed via ordinary CRUD. These details explain the operational effect beyond the raw destructive flag, making the behavior transparent without contradicting annotations.

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 concise—about four sentences—and front-loads the core purpose. It logically organizes mode explanations, prerequisites, and a behavioral note. No filler, and each sentence adds information. It could be slightly more structured (e.g., bullets) but is effective as is.

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 operation with multiple modes and prerequisites, the description covers the essential: what it does, mode distinctions, discovery requirement, source matching, verification behavior, and that it doesn't bundle. It doesn't mention overwriting behavior or error cases, but annotations cover destructiveness, and the schema covers tenant_binding. Given the complexity, this is fairly 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 description coverage is 0% per the context signal, though the input schema itself includes descriptions for stream_class and tenant_binding. The tool description adds meaning for 'mode' by explaining each enum value's semantics and for 'source' by tying it to discovered streams. However, it does not systematically describe all parameters (connector_id, schema) and relies on the schema's own field descriptions. This partial compensation yields a mid-range score.

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 clearly states the verb and resource: 'Bind source streams to the app's schemas.' It distinguishes from siblings like build_connect_data_source (which presumably connects a data source) and build_discover_source (which discovers streams) by focusing on the binding action and its modes. The purpose is unambiguous and specific.

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 gives clear usage context: it explains that live modes require discovery to have run, and that source must match a discovered stream. It also differentiates modes (live_read, live_readwrite, sync) and notes the admin-only restriction for live_readwrite. While it doesn't explicitly say 'use this instead of X', the prerequisites and mode selection provide strong guidance for when to invoke this tool.

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