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

Annotations already declare readOnlyHint=true, and the description adds tangible behavioral detail beyond that: 'Nothing is stored: the answer returns the package for the agent to keep,' plus the side-by-side reading behavior and the ambiguous-school 'nothing is read' rule. These are useful traits an agent cannot infer from the annotations alone.

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 dense but front-loaded with the primary action, then explains data transformation, user interaction, ambiguity handling, and storage behavior. Each sentence contributes distinct information; no filler or redundancy. Its length is justified by the tool's complexity, and the structure is logical.

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?

Given the tool's complex nested-object schema and the presence of an output schema, the description covers the necessary ground: what is read, how files are converted, how to handle ambiguous school names, user instructions, and the non-storage guarantee. It does not spell out every error condition or the output schema's content, but that is already available elsewhere.

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 the baseline is 3, but the description enriches parameter meaning by explaining what the tool does with each file ('each file's text and status, its courses and exams as rows') and how the data maps to what will_my_credits_transfer expects (courses as { unitid or school, code }; exams with score). This adds value beyond the schema's property descriptions.

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 opens with a specific verb and resource: 'Read a person's transcripts into their evidence package'. It then breaks down exactly what that means (file text/status, courses and exams as rows) and names the downstream sibling tool (will_my_credits_transfer). This clearly distinguishes it from the adjacent assemble_my_work_and_credentials and gives the agent an unambiguous sense of purpose.

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?

The description gives explicit operational guidance: ask the person for each transcript and its school, handle ambiguous school names by returning candidates and reading nothing, and send transcripts over multiple calls if needed. It does not name alternative tools to avoid or specify when not to use it, but the context and reference to will_my_credits_transfer make the intended scenario clear.

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