save_profile

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

Annotations declare destructiveHint=true and idempotentHint=true, and the description adds precisely the context those hints cannot: what is overwritten ('Replaces an earlier GatorPath profile at that path, never any other file'), what is refused ('refuses paths inside the GatorPath folder'), and the safety profile of the file ('plain text they can read, edit or delete, readable only by them'). It also scopes the data written (everything in the profile plus goal, chosen_electives, and the last plan that passed check_plan) and asserts 'Nothing else is stored anywhere.'

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 action and the hard usage gate, then a single dense paragraph covering file location, permissions, overwrite scope, and retention. Every clause carries information an agent could otherwise get wrong; there is no filler or restatement of the schema.

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 destructive write with no output schema, the definition covers location, overwrite scope, refusals, privacy, and retention, which is close to everything needed to call it safely. It does not say what the tool returns on success (e.g. the resolved path or a confirmation), which leaves one small gap for an agent deciding how to report the result.

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 description coverage is 0%, so the description must carry parameter meaning, and it does for `path`: default location, that it is a filesystem path on the student's machine, and a hard restriction against GatorPath-internal paths. For `profile` it explains the retention rule and the two fields added beyond the supplied profile (goal, chosen_electives) plus the last passing plan, but the large Profile schema's many undocumented fields (gpa, program, adt, etc.) receive no per-field meaning.

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 uses a specific verb+resource ('Save the student's profile') and states the payoff ('so the next session starts from it'), which implicitly distinguishes it from the load_profile sibling. It goes further to specify the concrete artifact produced (one YAML file at `path`), so an agent knows exactly what the tool does without opening the schema. It stops short of explicitly naming the sibling alternative, so it is not a full 5.

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 bolded '**Only when the student asks to save.**' is an explicit, unambiguous trigger condition that also functions as a when-not guardrail (do not proactively persist). No competing save tool exists among the siblings, so there is no alternative to route to. The absence of an explicit statement about what to do instead when the student has not asked (e.g. keep state in-session) keeps it from a 5.

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