Read Engine Storage

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description goes beyond them by disclosing the developer-role auth requirement and the behavioral difference between Postgres and other engines (vacuum/dead tuples vs reclaimable space). It also discloses a result cap ('largest 100 tables'), which matters for interpreting output. It does not mention cost/heaviness of the scan or pagination, keeping it short of 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?

A single dense sentence front-loads what is returned, followed by a short permission note; there is no filler. The enumeration is long but each item earns its place by describing a distinct metric. Slight deduction for cramming the auth note into the same sentence rather than separating 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?

As a read-only tool with no output schema, the description does a good job describing return contents and permissions, and it needs no return-value section. However, for a five-parameter tool with zero schema description coverage, leaving every scoping parameter undocumented is a real gap an agent must guess around.

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% across five parameters, so the description carries the full burden and does not deliver: workspaceSlug, appSlug, serviceName, env and region are never explained, and the env enum values are left entirely to the schema. The only parameter-adjacent remark ('Names the schema') is ambiguous and does not clarify how serviceName or env scope the query.

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 ('Returns') and enumerates exactly what the resource yields: per-database size, the largest 100 tables/collections with row counts, table and index bytes, dead tuples and vacuum state on Postgres, reclaimable space elsewhere, and unused indexes. This is clearly distinguishable from siblings such as readEngineKeyspace, readEngineSlowLog and streamEngineStats, which cover different engine telemetry.

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?

The description gives a stated prerequisite ('needs the developer role'), which helps an agent decide whether it can call at all, but it never says when to choose this over alternatives like streamEngineStats or readEngineKeyspace. Usage is only implied by the subject matter (storage/bloat investigation).

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