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

Annotations declare readOnlyHint=false, and the description explains why: it 'may download the source document and persist its parsed content in Scout's catalog', which is exactly the side-effect context an agent needs. It also discloses latency ('usually completes within 60 seconds') and that output is capped, adding value beyond the structured fields.

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 verb and resource, then side effects, then timing, then scope limitation — a sensible ordering with no filler. All four sentences carry information, though the closing negation could be folded into the opening scope statement.

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?

With no output schema, the description does cover the return shape (capped excerpts) and rules out full export, plus discloses the mutation, persistence, and timing. This is close to complete for a tool whose remaining parameters are well covered by the schema.

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 80%, so the schema already documents force/include/text_offset/max_text_chars in detail. The description only loosely gestures at the capping behavior ('capped excerpts'), adding little parameter-level meaning beyond what is already structured.

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 ('fetch and parse'), a precisely scoped resource ('one public 3GPP TDoc by number'), and the output shape ('capped excerpts'). An agent can distinguish it from the search_/list_tdoc siblings, but the description never differentiates it from the very similar 'get_tdoc' sibling, which is a real ambiguity.

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?

Provides a when-not ('Does not provide a whole-document export') that usefully rules out one class of intent. However, it gives no positive guidance on when to prefer it over get_tdoc or the search/list variants, leaving alternative selection to inference.

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