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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description still adds real behavioral context beyond them: the payload is 'cached' (potentially stale) and the patch suggestions are capped at three.

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?

One tightly written sentence, front-loaded with the action and the returned content, with no filler.

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?

An output schema exists, so return values need not be detailed, and the annotations carry the safety profile. The description supplies what is missing: what the payload is, how it is keyed, and that results are bounded.

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 0% and the single parameter has no description, but the phrase 'by exact ID' clarifies that inspection_id is an exact identifier rather than a name or search term. That partially compensates for the undocumented schema field, but format/constraints remain unstated.

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 gives a specific verb ('Read'), a concrete resource ('cached AI explanation and up to three suggested patch locations'), and a keying mode ('by exact ID'). It is clearly distinct from the list_* siblings, though it never names them 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?

'By exact ID' implies the agent must already possess an inspection_id (presumably from list_inspections), but the description never states that prerequisite or when this tool should be preferred over the list tools. Usage is only inferable.

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, idempotentHint, destructiveHint=false and a closed-world profile, so the safety story is covered. The description adds that results are a discovery seed for a later context call, but says nothing about pagination behavior, result ordering, or total-count semantics that matter for a list tool.

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 well-formed sentence with the discovery purpose front-loaded and the downstream dependency trailing. No waste, though it is arguably too terse for the information it leaves out.

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?

An output schema exists, so return-value shape need not be described. However, for a paginated list tool with 0% schema coverage, the absence of any statement about limit/offset, ordering, or expected volume leaves a real gap an agent would hit when results exceed the default limit of 20.

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% and the description never mentions limit or offset, even though pagination is the main behavioral concern for this tool. With two undocumented parameters and no compensating text, the agent must infer paging from names alone.

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 ('Discover') and resource ('persisted inspection IDs'), which tells the agent this is an enumeration tool that yields IDs rather than full records. It implicitly distinguishes itself from get_inspection_context by positioning itself as the ID-discovery step, though it never names the sibling 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?

'before requesting their cached context' gives explicit sequencing guidance that routes the agent to call this before get_inspection_context. It gives a clear context of use but offers no exclusions or detail on when this is unnecessary (e.g., if IDs are already known).

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, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds two genuine behavioral facts the annotations do not: the result ordering ("Oculus order") and that live forge data is not fetched, so results may be stale/metadata-only. It does not cover pagination behavior or result volume.

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 front-loaded sentence with no filler; the scope negation is appended efficiently. It is arguably too terse for the gaps it leaves, but there is no wasted text.

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?

An output schema exists, so return values need not be described, and annotations carry the safety profile. However, pagination semantics are absent from both schema and description, and the undefined jargon (Oculus order, forge data) leaves an agent without a clear mental model of the result set.

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%, so both limit and offset are undocumented in the schema, and the description never mentions pagination, defaults of 20/0, or the maximum of 50. For a two-parameter list tool the description is the only place this could be explained, and it isn't.

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 verb+resource is identifiable ("Read saved activity metadata"), but "saved activity" and "Oculus order" are unexplained domain jargon, and the description does nothing to distinguish this from siblings like list_tracked_projects or list_inspections. The negation ("does not fetch live forge data") narrows scope somewhat but doesn't clarify what is returned.

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?

There is no when-to-use guidance, no statement of prerequisites, and no reference to any alternative tool. The only hint is the negative constraint about live forge data, which an agent could infer as an exclusion but is never framed as such.

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, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds that results include the Oculus group hierarchy, which is useful shape information, but says nothing about pagination behavior despite exposing limit/offset.

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 front-loaded sentence with no filler. It is appropriately sized, though its brevity comes partly from omitting pagination and usage context.

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?

An output schema exists, so return values need not be described. The gap is that the two pagination parameters go entirely undocumented, leaving the tool minimally adequate rather than complete.

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%, so neither limit (max 50, default 20) nor offset is explained anywhere. The description does not mention pagination at all, leaving the agent to guess that these control result windowing.

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 (Read) and resource (tracked GitHub/Codeberg projects) plus the Oculus group hierarchy it returns. It's clearly distinct from list_inspections and list_saved_items, though it never explicitly contrasts itself with those siblings.

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?

There is no guidance on when to call this versus list_saved_items or list_inspections, nor any prerequisites or exclusions. The agent must infer usage purely from the resource noun.

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