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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds that this is a GET /templates/ call returning field metadata per record type, which is meaningful since there is no output schema. Auth, rate limits, and pagination behavior are unstated, 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?

Two compact sentences: the first front-loads what is returned and for which record types, the second immediately gives the actionable use case. No filler or restatement of the title beyond what's necessary.

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 zero-param read tool with no output schema, the description adequately conveys what comes back (field names, labels, types, options per record type) and why. Only minor omissions like response shape details or empty/error behavior keep it from a 5.

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?

Zero parameters, so the baseline of 4 applies; the description does not need to explain inputs and correctly doesn't waste words on them.

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?

Names a specific resource (account templates / field definitions) and enumerates the exact content returned: names, labels, types, options, per record type (contacts, companies, deals, cases, tasks). This clearly separates it from the record-fetching siblings like cogmento_get_account or cogmento_list_contacts, though the verb itself is left implicit in a noun phrase.

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?

Explicitly states the use case: 'Use it to learn the custom field names for filters, creates and field updates,' which effectively points the agent at the create/update/filter siblings as downstream consumers. No explicit exclusions or when-not conditions, but none are really needed for a single zero-param metadata endpoint.

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