Add application

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

Describes return behavior: 'Returns the created application and possible-duplicate warnings'. Discloses duplicate detection and user instruction. Annotations have readOnlyHint=false and destructiveHint=false, which align with a create operation. No contradictions.

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 extremely concise: two sentences plus an example. It is front-loaded with the core purpose and immediately provides usage clarity. Every sentence is informative with no fluff.

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 complex tool with 19 parameters and no output schema, the description covers the key behaviors (two input modes, duplicate warnings). It might lack guidance on parameter combinations, but it is sufficiently complete for an AI to use correctly.

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 74% schema coverage, the description adds value by providing an example for the raw parameter and clarifying that company and role are required in structured mode. It doesn't re-describe all parameters, but the schema already covers them adequately.

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 tool's purpose: 'Track a new job application.' It explains both usage modes (raw line or structured fields) and distinguishes from sibling tools like list_applications and update_application by being a create operation.

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 guidance on when to use raw vs structured fields: 'Pass either a single raw line... or structured fields'. Also instructs on handling duplicates: 'if duplicates are listed, tell the user instead of creating again'. Missing explicit when-not-to-use, but covers common scenarios well.

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