read_course_resource

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description's download-and-extract framing is consistent with a read operation, so there is no annotation contradiction. The description adds modest context by naming the supported file formats (PDF, Office, text). However, it does not disclose truncation behavior implied by max_bytes/max_chars/max_pdf_pages, what happens on extraction failure, or the shape of the returned text — with annotations covering the safety profile, this is adequate but not rich.

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 a single efficient sentence with no filler or repetition, earning strong conciseness marks. The minor structural flaw is that the vague phrase 'una referencia reciente' consumes space without adding clarity — it muddies the sentence instead of front-loading the precise object of the action.

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 tool with 4 parameters, no output schema, and 0% schema description coverage, this description is not complete enough. It omits what resource_token refers to, the meaning of 'recent reference', the behavior of the three limit parameters, and what the tool returns (presumably extracted text). An agent has to guess at these, which is a meaningful gap for a moderately complex tool.

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 carries the full burden of explaining the 4 parameters, and it only partially does. The mention of 'PDF, Office o texto' loosely hints at why max_pdf_pages exists, but resource_token is never explained as a course resource identifier, and the limit mechanics of max_bytes/max_chars/max_pdf_pages (truncation thresholds) are undocumented in both schema and description. The compensation is insufficient for zero-coverage input.

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 states a concrete action — download a resource via HTTP and extract text from PDF, Office, or text formats — which conveys the core function. However, 'una referencia reciente' (a recent reference) is vague and never clarifies what a course resource is, and the description makes no attempt to distinguish itself from closely related siblings like list_course_resources and list_course_contents. The verb+resource is recognizable but the phrasing is ambiguous enough to land below a 4.

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?

There is no guidance on when to use this tool versus the many sibling tools (especially list_course_resources, which an agent must decide against). No when-to-use, when-not-to-use, or alternative-routing information is provided. An agent must infer from the name alone that this is the tool for actually fetching resource content, which is risky.

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