Get a Microsoft subscription, or search them

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

Annotations already carry read-only, idempotent, open-world, and non-destructive safety, and the description reinforces that with 'reads the subscription record only — nothing here manages the tenant'. It adds useful behavioral context: using it is non-managing, and it exposes the tenant boundary. It doesn't mention pagination, but that behavior is already described inside the page/size parameters.

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 sentences, no filler, with the primary return semantics first and the alternative search mode second. The one-sentence sibling pointer is efficient. It packs a lot of meaning without bloating, though it could have been even shorter by omitting the parenthetical account-label phrase inside the first sentence, since the parameter schema already says it.

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 an 8-parameter, 0-required, read-only tool with an output schema and 100% schema parameter coverage, the description is complete. It explains the get-vs-search behavior, names the all-products sibling, and confirms the read-only/non-tenant-managing nature. Nothing an agent needs to choose or call it correctly is missing.

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 coverage is 100%, so the schema already documents all 8 parameters. The description does not repeat parameter docs, which is correct. It adds meaning by explaining the id-omitted search semantics and reinforcing that sortField is spelled as in response items, when/where that matters. The description also clarifies the overall mode switch that gives meaning to id vs. filters.

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 names a specific verb (returns one subscription or searches them) and resource (Microsoft 365 subscriptions), lists the identity/status/domain/term fields, and distinguishes it from eurodns_subscription_search. It also notes that the sibling covers every product at once, so an agent can tell this from eurodns_email_get_subscription and eurodns_ssl_get_subscription too.

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?

It explicitly says searches by status, domain and account label when id is omitted, which is exactly the mode-switch an agent needs to decide between a single-object get and a search. It differentiates from eurodns_subscription_search by saying 'every product at once is eurodns_subscription_search'. It does not list the other per-product getters by name, but the schema params are Microsoft-specific, so the sibling list plus the phrase 'Microsoft subscription' gives enough route.

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