misakanet_submit_intake

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

Despite no annotations, the description discloses side effects ('writes to data/contribution_queue.jsonl'), auth requirements ('none'), rate limits ('local stdio process only'), and data handling (auto-redaction before persistence). It also warns about not including raw logs/prompts/secrets, which is rich behavioral context. It also specifies the output schema's return fields, which is helpful.

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?

Dense but well-organized: purpose first, then when-to-use, then parameter semantics summary, then side effects and warnings. Each sentence serves a purpose and conveys multiple pieces of information without fluff. The format is scannable and front-loaded with the most important 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 tool with 8 parameters but only 1 required, this description covers all the key behavioral dimensions: when to use, parameters semantics, side effects, security/redaction behavior, and expected output. No output schema exists, yet the description still outlines the output, which is complete. The complexity justifies this length, and it earns its conciseness.

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 100%, so all parameters are documented there. The description adds value by clarifying which are required vs optional ('problem is required'), the default value for kind ('kind defaults to missing_lesson'), and the semantics of kind values. It does not repeat each schema description but synthesizes the important distinctions. Slight redundancy with schema but with the highest information density.

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?

Clear verb phrase and resource: 'Submit a failure-case intake'. It specifies the action, when to use it in relation to sibling misakanet_search, and for what kind of content. The 'Use after misakanet_search fails...' clause provides scoping. Differentiates itself from siblings by describing the workflow (post-search use case).

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?

Explicitly states when to use this tool vs alternatives in the first two sentences: 'Use after misakanet_search fails to find a good match, or when the user resolved a problem not yet documented.' This provides concrete preconditions and a workflow trigger, naming the sibling tool.

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