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

Annotations already cover read-only, idempotent, closed-world and non-destructive, so the bar is lower; the description nevertheless adds real behavior: the data is read live from the account, the collection list may be incomplete signalled by totals.truncated, and catalog collections are read-only. It doesn't cover auth/permission needs or response shape details, keeping it below a 5.

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 well with the core action in the first clause, and most sentences carry information (truncation, source semantics, fixity of counts). However, the closing sentence about catalog and unfiled titles 'the user did not choose; they belong to the same account all the same' is editorial padding that restates the source meanings.

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 needn't be explained, yet the description spends much of its length on payload semantics while omitting the one thing the schema doesn't document: the required targetLang argument. For a single-parameter context loader this leaves a real gap an agent must guess around.

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?

There is one required parameter, targetLang, with 0% schema description coverage, so the description carries the full burden — and it never mentions the parameter at all. An agent gets no guidance on whether targetLang is an ISO code, a display name, or what values are valid.

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 ('Returns the user's current Lingard learning context, read live from their account') and enumerates the payload (profile, vocab totals, collections, card counts, missing-field stats). This clearly separates it from narrower siblings like lingard_get_vocab_collection or lingard_get_collection_gaps, though it never names an alternative explicitly.

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 line 'Earlier answers in the conversation may be out of date; this is the account as it stands now' implies the refresh/reload use case, which is genuine usage guidance. But there is no when-not-to-use statement and no routing to siblings such as lingard_get_collection_gaps or lingard_get_vocab_collection for narrower reads.

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