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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds real value beyond that: it discloses the direction limitation and, crucially, that complete=false signals partial metadata extraction rather than authoritative lineage. That caveat is exactly the kind of behavioral transparency structured fields cannot carry.

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 short sentences, front-loaded with the core purpose and the direction constraint. No wasted words; the completeness caveat is appropriately placed last. Minor awkwardness in 'with evidence' but overall tight.

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 explained, and the complete=false caveat adds valuable context. Still, for a 6-parameter tool with 0% schema coverage, the description leaves most parameter semantics unexplained, making it only adequately 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% across 6 parameters, so the description bears full responsibility. It only touches 'direction' (DOWNSTREAM/BOTH unsupported) and leaves max_depth bounds, environment, space, object_type, and technical_name format entirely undocumented in prose. With low coverage and many params, the description fails to compensate.

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: infer bounded upstream CSN dependencies, with the qualifier 'with evidence'. This is distinguishable from siblings like get_object or list_objects, though the CSN/lineage domain jargon may not be self-evident. Clear but minimal sibling differentiation.

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?

Provides a useful when-not: DOWNSTREAM/BOTH are unsupported, which routes the agent away from an invalid direction. However, it gives no positive when-to-use guidance or explicit alternative (e.g., when to choose this over get_object). Usage is implied rather than spelled out.

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 openWorldHint, so the safety profile is fully covered structurally. The description adds one genuinely useful behavioral detail beyond that: secrets are redacted while other metadata is preserved. It says nothing about auth requirements, error behavior, or size/rate limits on large definitions.

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 tightly written sentence with no filler, and the core operation is front-loaded. It is arguably too terse for a four-required-parameter tool, but nothing in it is 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?

An output schema exists, so return-value documentation is not needed, and annotations cover the safety profile. Still missing for a four-parameter lookup tool is any indication of which object_type values matter, what happens on a missing object, or how this fits alongside get_dependencies.

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 four required parameters, so the description must carry the load and does not: it never explains environment, space, object_type, or technical_name. The enums and patterns in the schema partially self-document environment and object_type, but the description contributes no semantics at all.

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 ('the original SAP CSN/JSON definition'), so the agent knows it retrieves a single object's raw definition rather than a list. It does not explicitly contrast with siblings like list_objects or get_dependencies, but the get-vs-list distinction is inferable from the name and phrasing.

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 reach for this tool versus list_objects or get_dependencies, and no mention of preconditions such as needing a known technical_name or a valid environment/space combination. Usage must be entirely inferred from the tool name.

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 readOnly, idempotent, openWorld, and non-destructive behavior, so the safety profile is covered. The description does add pagination continuity via 'next_offset' for additional pages, which is genuine value beyond annotations, but omits rate limits, result ordering, or whether paging can go stale.

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 compact sentence with the primary action front-loaded and no filler. It is arguably too terse given the undocumented parameters, and 'verified CLI type' is vague phrasing, but nothing is 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?

With five parameters at 0% schema coverage, this tool needs more descriptive support than one sentence. An output schema exists, so return values need not be explained, but the scoping parameters (environment, space) and pagination limits are never clarified, leaving the agent to infer the core calling contract.

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. It lightly clarifies object_type ('verified CLI type') and alludes to offset-style paging, but says nothing about environment, space, limit, or offset semantics, leaving most parameters undocumented in both places. It also names 'next_offset' while the actual parameter is 'offset'.

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 ('List modeling objects') and constrains it to 'a verified CLI type,' which maps to the object_type enum. It distinguishes the tool well enough from get_object (single retrieval) but never explicitly contrasts with list_spaces, the closest sibling.

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 statement of when to use this tool versus get_object, get_dependencies, or list_spaces. The only procedural cue, 'follow next_offset for additional pages,' describes how to keep paging once invoked, not when this tool is the right choice.

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, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds 'bounded pagination,' which is the one piece of behavioral context beyond the annotations, though the actual bound is only visible in the schema's maximum=200.

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 front-loaded sentences with no filler; the core action comes first and the constraints follow. It is arguably under-specified rather than padded, so it scores well on waste but not on completeness.

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?

The output schema means return values need not be explained, which reduces the burden. Still, for a tool with a required enum parameter and zero schema descriptions, the description should say what environments mean and how paging works; it only alludes to both.

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 the description must carry the load for three parameters and largely does not. 'Explicit environment' notes that environment is required but never explains the DEV/QAS/PRD enum, and 'bounded pagination' gestures at limit/offset without describing their semantics or interaction.

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+resource ('List accessible spaces'), so an agent knows this enumerates spaces rather than objects. However, it makes no attempt to distinguish itself from siblings like list_objects or get_object beyond the noun, leaving the boundary 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?

There is no when-to-use guidance, no mention of when to prefer list_objects, and no stated prerequisites or exclusions. 'Explicit environment' hints that environment is mandatory but that is already declared in the schema's required list.

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