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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint. Beyond that, the description adds a genuine data-boundary disclosure: it reads only the key-linked project and explicitly not clients, forms, payments, or other projects' content. That is real behavioral context about access limits. It stops short of explaining the temporary-key auth mechanism or the response shape.

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 tight sentences, zero filler, with the positive scope stated first and the exclusions second. Nothing is repeated from the name or 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?

For a parameterless read tool with no output schema, the description covers scope well but never describes what comes back (connection state, project info) or how errors surface. Since no output schema exists, that return-value context would have been the description's job to carry.

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?

The tool takes zero parameters, so there is nothing to document and no schema gap to compensate for. Baseline 4 applies; the description offers no parameter detail because none is needed.

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 states a specific read action and, crucially, its scope: it only consults the project tied to the temporary key. This lets an agent separate it from siblings like inspect_site and send_draft. However, it never says what the tool actually returns (connection status, project metadata), which the name connection_info implies but the text leaves implicit.

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 implicitly frames when the tool is appropriate by declaring its narrow scope, and the exclusions hint at when NOT to rely on it for other data. But no alternative tool is named and no explicit condition selecting this over inspect_site is given.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, and the description is consistent, adding that it only reads a pre-authorized folder and never sends files or executes commands. The phrase "previamente autorizada" usefully implies an authorization prerequisite, though rate limits/return behavior are unstated.

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 with zero filler: the positive scope comes first, followed by the negative boundary. Nothing is repeated or wasted.

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-parameter, read-only inspection tool with no output schema, the description covers what is examined and what is not performed. It stops short of describing the shape of the inspection result, which an agent might want, but the safety profile is fully covered by annotations.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies the input is a pre-authorized static folder rather than anything the agent supplies at call time, which is the only semantically relevant point.

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 (verifies/inspects) and resource (the previously authorized static folder), enumerating what is checked: files, size, recognized credentials. It implicitly separates itself from send_draft by declaring it neither sends files nor runs commands, though it does not name that sibling directly.

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 exclusion clause ("Não envia arquivos nem executa comandos") hints at the boundary with send_draft, but there is no explicit statement of when to call this versus connection_info or send_draft. Usage is implied rather than directed.

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

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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds useful beyond-annotation context: it consumes the existing quota and explicitly does not publish, substitute or delete themes. This clarifies the side-effect profile rather than just restating annotations.

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?

Three short sentences, front-loaded with the core action, then quota/side-effect constraints, then the publishing note. No filler; each sentence carries information the agent needs.

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 action with no output schema, the description covers what is sent and what it does not do, but says nothing about the result of a successful or failed send (no confirmation, return, or quota-exhaustion behavior). Adequate but leaves the agent guessing about outcomes.

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?

The tool takes zero parameters, so the schema carries no per-parameter meaning to supplement. Baseline for a 0-param tool is 4; nothing in the description is needed to disambiguate arguments.

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 and resource: it sends the authorized static folder as a draft ('Envia a pasta estática autorizada como rascunho'). The action is clearly distinct from the read-oriented siblings inspect_site and connection_info, though no sibling is named explicitly.

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?

Gives real context: it respects an existing quota and explicitly does not publish, replace or delete themes, with publishing left to the user in the panel. That sets a clear boundary on when this tool applies versus the manual publishing flow, though it does not route to any MCP alternative.

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