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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true. The description adds genuinely useful behavioral context beyond them: the operation is non-interrupting ('without stopping it'), it applies across multiple application states, and it carries a strong 'never add facts' constraint. It does not address the destructive/mutating nature directly, but the added operational context is substantial.

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, then usage conditions, then concrete examples, then constraints, then parameter sourcing. Despite its length, every sentence carries distinct, actionable information with no repetition.

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?

An output schema exists, so return values need not be described. Combined with the annotations, the description covers triggers, state applicability, the session_id dependency, and behavioral constraints – everything needed to invoke the tool 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?

Schema coverage is only 50% (session_id has no description), so the description must compensate, and it does: it names the session_id's source ('from apply_for_job or list_active_applications') and elaborates the instructions parameter's intended content ('their wish as plain instructions with their exact facts; never add facts'). This adds real meaning beyond the schema.

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 ('Change what an application in progress fills in') with the key differentiator 'without stopping it.' An agent can immediately distinguish this from apply_for_job, stop_application, and submit_application among the siblings.

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?

Names explicit trigger conditions with user-utterance examples, states the states in which it works (running, ready to submit, waiting for answers), and routes to save_about_me for a related but distinct need. When/when-not and alternatives are all covered.

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