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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds genuinely new context: it works while the application is running, ready to submit, or waiting for answers, and it constrains input ('never add facts'). It stops short of saying whether a change is reversible or how it interacts with an in-flight submission, so it falls just short of full transparency.

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 the operation and its condition, then prerequisites and the save_about_me pointer. The parenthetical examples are somewhat heavy but each maps to a real distinct use case rather than padding.

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 no explanation. With the trigger condition, validity window, session_id provenance, input constraints, and the persistent-facts alternative all present, an agent has everything required to invoke this 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 50% — only 'instructions' is described in the schema. The description compensates by stating where session_id comes from (apply_for_job or list_active_applications) and by defining the expected content of instructions (plain words, user's exact facts, no invented facts). That is meaningful added semantics 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 an explicit scope qualifier ('without stopping it') that separates it from stop_application and apply_for_job. The title/name pairing plus the concrete examples make the operation unambiguous.

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?

Gives the exact triggering condition (the user says something about an application filling right now) plus four quoted utterances that map to it, and names an alternative path (save_about_me) for facts meant to persist. An agent can decide when to call this without inference.

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