source_binding_suggest

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

There are no annotations, so the description carries the burden. It explicitly discloses the read-only nature of the tool, which is the most important behavioral default. It does not mention response shape, staleness, or failure behavior, but the core side-effect profile is handled clearly.

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?

Two sentences, no fluff, and critical guidance is front-loaded.

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?

Defines the operation's role and read-only nature, and pairs it with the accept sibling nicely. However, with no output schema, the agent is left without knowing what a suggestion looks like, and unclear params (includeStructured, taskContextId) reduce completeness.

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?

With 0% schema description coverage, the description must compensate. It doesn't explain parameters like taskContextId, includeStructured, limit, or maxFiles beyond their namesaren't self-sufficient. The phrase 'from AST symbols and project semantics' provides thematic context but not parameter-level meaning.

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 uses a specific verb and resource—'Suggest source bindings for a Block'—and clarifies the input domain ('from AST symbols and project semantics'). It also distinguishes the tool from source_binding_accept by explicitly naming the sibling as the persistence step. An agent can tell exactly what this tool does and what it is not.

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 explicit usage guidance: suggestions are read-onlyaint, and if you want to commit an explicitly chosen candidate you should use source_binding_accept. This clearly separates the tool from its sibling and tells the agent when not to use it.

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