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

Annotations already declare readOnly, idempotent, and non-destructive, so safety is covered. The description goes beyond them by defining the return payload ({items:[{code, url, handle}]}) and by disclosing that project_id is inferred for single-project customers, which materially affects how the tool will behave.

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 purpose in the first clause, then usage, then return shape, then the parameter caveat — a sensible order with no filler. Two of the sentences are densely packed with backtick-heavy notation, which is efficient but slightly hard to scan.

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?

With no output schema, the description correctly supplies the return shape and field meanings (custom_<code>, handle as join key). For a one-parameter read tool this covers nearly everything an agent needs, though it omits error/no-sources behavior.

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% on the single parameter, so the description must carry the load and largely does: it marks project_id as OPTIONAL and explains the single-project inference fallback. It does not state what happens for multi-project customers (error vs. all projects), which is the remaining gap.

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 and resource ('List the AI sources currently registered on a project') and ties the resource to its mutation sibling by noting attributes are 'populated via set_ai_source'. That distinguishes it from set_ai_source, delete_ai_source, and list_api_sources without opening a 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?

'Use this to see which AI sources a project already has' restates the purpose rather than defining a decision point. It gives no guidance on when to prefer list_api_sources or list_source_attributes instead, so the agent must infer the boundary from sibling names.

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