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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and non-destructive, so safety is covered. The description adds the valuable behavioral detail that this is the *full* record — including derived/related data such as phase history and linked quotations — which is not derivable from annotations or the one-parameter schema.

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?

Two short sentences, front-loaded with the payload enumeration and finished with an API reference. No filler, no restatement of the title.

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 carries the burden of telling the agent what comes back, and it does so thoroughly for a read-only single-record fetch. What is missing is only secondary: error behavior for an invalid/unknown deal_id and the absence of an explicit pointer to the list 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 100% and the single deal_id parameter is documented in the schema as a UUID with a regex pattern. The description adds no parameter-level detail (e.g. how to obtain a deal_id), so the baseline 3 applies.

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?

Specific verb ("fetch") plus resource ("one deal") plus an enumeration of exactly what is returned (lead, value, probability, phase history, quotations, custom fields). The word "one" cleanly separates it from the sibling teamleader_list_deals, and the included-field list separates it from teamleader_create_deal or the contact/company getters.

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?

Usage is implied: it needs a known deal_id, so it is the single-record lookup rather than the list. However, no alternative is named explicitly (teamleader_list_deals is never mentioned), and there is no statement of when-not-to-use or what to do if you only have a name instead of a UUID.

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