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

With no annotations, the description carries the full burden. It usefully discloses one behavioral trait: absent or unsupported configuration is reported rather than erroring. It does not state that it is read-only, what permissions are required, or that it likely fans out into several underlying API calls.

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 front-loaded sentence with the verb first and no filler. It is appropriately sized, though the trailing clause about absent configs could be seen as slightly compressed.

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?

No output schema exists, so the description should ideally sketch the shape of the multi-domain response; it only notes the absent/unsupported handling. Adequate but leaves the return structure and the bucket parameter unaddressed.

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 'bucket' parameter is never mentioned, described, or exemplified in the description. For a tool whose only input is a bucket identifier, the description adds no meaning about format or required identifier.

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?

Clear verb+resource ('Read ... bucket config') and it enumerates the exact configuration domains fetched: location, versioning, CORS, policy, Object Lock. This implicitly separates it from the object-oriented siblings (s3_get_object, s3_head_object, etc.), though it never explicitly names an alternative.

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?

No statement of when to reach for this tool versus the many s3_list_* / s3_get_object variants. The agent must infer that this is the bucket-level inspection call. No prerequisites or exclusion conditions are 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?

With no annotations, the description carries the full behavioral burden and does disclose two meaningful traits: a hard 262144-byte truncation cap and that content is returned as text or base64. It omits permission requirements, error behavior for missing keys, and whether truncated output is flagged, leaving real gaps for a read tool with zero annotation coverage.

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 with the size constraint and output format front-loaded, followed immediately by the routing alternative. No filler; every clause carries information.

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 read tool with no annotations and no output schema, the description covers the essential size/encoding behavior but leaves key gaps: version_id handling, truncation signaling, and failure modes. Adequate to call the tool, not complete for an agent to do so confidently.

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% with 5 parameters, so the description must compensate. It partially does: the byte cap implies max_bytes and 'text/base64' implies encoding, but version_id is never mentioned and its semantics are undocumented in both schema and description.

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 (read an S3 object) plus a concrete scope for the operation (at most 262144 bytes, inline as text/base64). It explicitly distinguishes itself from s3_presign_get, but says nothing about how it differs from near-neighbors like s3_head_object or s3_preview_object, so the differentiation is partial.

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 an explicit when-not condition ('use presign for larger objects') and names the alternative tool, which is exactly the routing decision an agent needs. It stops short of a full when/when-not picture because it never addresses metadata-only (s3_head_object) or preview (s3_preview_object) use cases.

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?

No annotations are provided, so the description carries the full behavioral burden, and it discloses almost nothing: no required permissions, no behavior for untagged objects (empty tag set vs. missing-tag error), no versioning interaction with version_id, and no error semantics. The only signal is the implicit read-only nature of "Get".

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 four-word sentence — there is no padding or buried lead, but the brevity stems from under-specification rather than disciplined editing. It is front-loaded only in the trivial sense that there is nothing else to order.

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 three-parameter tool with zero annotation coverage and no output schema, the description is far too thin. It does not cover parameter behavior, permissions, or the shape of the tag result, so the agent lacks the context needed to invoke it confidently in edge cases.

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 three parameters, and the description adds no parameter meaning at all. While bucket/key/version_id follow familiar S3 conventions, version_id in particular is undocumented — an agent gets no indication whether omitting it targets the current version or the latest tagging state.

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?

"Get object tags" states a verb (get) and a resource (an object's tags), so the operation itself is unambiguous. However, it is essentially a restatement of the tool name with no differentiation from siblings such as s3_get_object or s3_head_object, leaving the agent to infer where tag retrieval fits in the S3 read family.

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, when-not-to-use, or alternative-tool guidance anywhere in the description. The agent must guess whether this is meant for auditing tag sets, pre-delete checks, or general metadata reads, and must infer relationships with s3_get_object and s3_get_bucket_config on its own.

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?

No annotations are provided, so the description carries the full behavioral burden. It does not disclose that no object body is returned, whether permissions/403 errors are common, whether a version_id is required for non-current versions, or what metadata fields come back. Only the implied read-only nature of 'Read' is conveyed.

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?

It is a single front-loaded sentence with no filler, which is structurally clean. But brevity here tips into under-specification: the sentence is too small to carry the tool's semantics rather than genuinely efficient.

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 no annotations, no output schema, and 0% parameter coverage, an agent lacks everything it needs to call this correctly. Details on version_id usage, the metadata-only return, and error conditions are all 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 description coverage is 0%, so the description must compensate and does not. The three parameters (bucket, key, version_id) are only inferable from their names; the description adds no meaning, format, or requirement details beyond the schema property names.

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?

'Read object metadata' names a specific verb (read) and resource (object metadata), which is clearer than a tautology. However, it does not differentiate from close siblings like s3_get_object or s3_get_object_tagging, so an agent can't tell from the text alone why HEAD-style metadata retrieval is the right pick over a full GET.

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 use this tool versus alternatives such as s3_get_object (content) or s3_get_object_tagging (tags). The distinction only surfaces semantically if the agent already knows S3 HEAD semantics; the description never states it.

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?

No annotations are provided, so the description carries the full burden. It usefully discloses bounded scanning, default max_scan=10000, and that partial results carry a continuation token. However, it omits read-only nature, permissions, cost/latency implications, and whether max_scan counts objects or bytes.

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?

Single compact sentence, front-loaded with the core operation and key constraint. No fluff, but its brevity comes at the cost of missing parameter and usage detail.

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 5-parameter scan with no annotations or output schema, the description is too thin. It omits the roles of bucket, prefix, and limit, the relationship between limit and max_scan, how 'largest' is defined or ordered, and what the response contains.

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% across 5 parameters. The description only addresses max_scan and continuation_token, leaving bucket, prefix, and limit undefined, and does not clarify how limit differs from max_scan.

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 operation (scan for largest objects) and a key constraint (bounded with default max_scan). It does not differentiate from siblings like s3_list_objects or s3_prefix_usage, which also enumerate bucket contents.

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?

No guidance on when to choose this over s3_list_objects or s3_prefix_usage, nor any prerequisites. The default max_scan and continuation token are parameter behavior, not selection criteria.

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?

No annotations are provided, so the description carries the full behavioral burden. It discloses 'visible' buckets and pagination, which adds useful context beyond the schema, but omits auth requirements, return format, and whether visibility is account-scoped or permission-scoped.

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 short sentence with no waste, front-loading the action and resource. It is appropriately sized for a simple list operation.

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 tool with no annotations, no output schema, and zero schema description coverage on 2 parameters, the description is minimal. It leaves parameter meaning, return shape, and pagination mechanics unexplained.

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 description mentions only 'pagination', which loosely corresponds to max_keys and continuation_token. It does not explain the relationship between the parameters or their syntax, leaving most semantics undocumented.

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: listing buckets. It is distinguishable from siblings like s3_list_objects or s3_list_object_versions by the resource 'buckets'. However, it doesn't call out the distinction explicitly, so an agent must infer it from the resource name.

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 mention of 'visible' and 'pagination' implies usage context, but no explicit when-to-use, when-not-to-use, or sibling alternatives are given. An agent gets a weak signal without direction.

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?

No annotations are provided, so the description carries the full disclosure burden. It hints that results are paginated via markers, but does not state read-only safety, required permissions, whether results are scoped by bucket/prefix, or what the response contains.

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 terse, front-loaded clauses with no padding. It is appropriately sized for a short definition, though the second clause is too compressed to be useful.

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 no annotations, no output schema, and 0% parameter coverage across 5 parameters, the description is far too thin for the complexity. An agent cannot determine filtering behavior, permission needs, or return shape from this text.

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% for 5 parameters, so the description must compensate and largely does not. The cryptic phrase "both returned markers" ambiguously gestures at continuation_token/upload_id while bucket, prefix, and max_keys remain completely unexplained.

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 clear verb+resource ("List unfinished uploads"), which is better than a tautology. However, it does not differentiate from near-duplicate siblings such as s3_list_parts and s3_unfinished_uploads, leaving the agent to guess which is appropriate.

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 only guidance is "pass both returned markers," which is a pagination instruction rather than a when-to-use rule. There is no indication of when this is preferable to s3_list_parts or s3_unfinished_uploads, nor any prerequisites.

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?

With no annotations, the description carries the full burden. It discloses a page limit of 1000 objects and implies pagination, but doesn't explain that continuation_token is used for pagination, what happens when no prefix is given, or any permissions or rate limits. This is insufficient for a tool with four 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?

The description is a single sentence with no wasted words, though it could benefit from being more front-loaded with essential information about pagination.

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?

Given four parameters, no annotations, and no output schema, the description is too sparse. It fails to explain pagination, the role of continuation_token, or how to correctly scope the listing, leaving an agent likely to misuse the tool.

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 compensate. It only mentions 'scoped prefix' and '1000 objects per page', which loosely maps to prefix and max_keys, but provides no meaning for bucket or continuation_token, leaving critical parameters undocumented.

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 the operation (list) and the resource (objects under a scoped prefix), and mentions a page limit of 1000. However, it doesn't clearly distinguish itself from sibling list tools like s3_list_object_versions or s3_list_parts, and lacks explicit S3 context.

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 use this tool versus alternatives such as s3_prefix_usage or s3_largest_objects. The mention of a 'scoped prefix' implies usage but doesn't specify when or why to choose this over other listing methods.

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?

No annotations are provided, so the description carries the full burden. It reveals that delete markers are surfaced (a useful behavioral trait), but says nothing about permissions, ordering, how to iterate pages, or cost/rate characteristics of a versioned listing.

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 tight, front-loaded sentence with no waste. It is slightly cryptic ('both pagination markers' rather than naming the markers), but efficient overall.

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 5-parameter listing tool with no annotations and no output schema, the description is far too thin. It does not compensate for the absent parameter documentation or explain the pagination loop an agent must run.

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 5 parameters. The phrase 'both pagination markers' obliquely gestures at version_marker and continuation_token, but bucket, prefix, and max_keys are undocumented, and the description gives no syntax or semantics for any of them.

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 (List) and resource (object versions), and adds the notable scope detail that delete markers are included. This implicitly distinguishes it from s3_list_objects, which lists only current objects, though the sibling is never named.

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?

No when-to-use guidance, no prerequisites, and no mention of alternatives like s3_list_objects or s3_list_multipart_uploads. The agent must infer that this is the versioned-listing variant purely 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?

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing: no pagination behavior, no note that results are only meaningful for an active upload, no auth/permission requirements, no error semantics for expired upload IDs.

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?

The single sentence is short but that brevity reflects under-specification rather than economy. There is no structure, no front-loaded context, and nothing to help an agent act correctly.

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 no annotations, no output schema, and 5 completely undocumented parameters, the definition is inadequate for an agent to invoke this tool correctly. It fails to convey required inputs' meaning or expected return shape.

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 5 parameters (bucket, key, upload_id, max_keys, continuation_token), and the description adds no meaning for any of them. Notably, it never explains that upload_id identifies the upload whose parts are being listed, nor how max_keys/continuation_token drive pagination.

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 'List multipart parts' essentially restates the tool name (s3_list_parts) without adding distinguishing detail. It does not clarify that these are parts belonging to a single in-progress multipart upload, which is the key distinction from the sibling s3_list_multipart_uploads.

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?

No guidance whatsoever on when to use this tool, what prerequisites exist (a valid upload_id from an in-progress multipart upload), or how it relates to s3_list_multipart_uploads and s3_unfinished_uploads.

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?

No annotations are provided, so the description carries the full disclosure burden, and it delivers very little. "Bounded" implies scan limits via max_scan and "paginate" implies a paged result set, but the description never states what the bound is, what permissions are needed, whether the operation is a read or a scan with cost implications, or what the aggregate rows contain.

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 short sentence, front-loaded with the scoping idea and followed by the pagination note; there is no filler. It is appropriately brief, though brevity here borders on under-specification rather than discipline.

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 five-parameter tool with zero schema descriptions, no annotations, and no output schema, the description leaves critical gaps: it never explains what "usage" is, how the aggregate is computed, why the scan is bounded, or how pagination terminates. An agent cannot confidently invoke this from the definition alone.

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 (bucket, prefix, max_scan, result_offset, continuation_token), so the description is required to compensate and does not. Worse, it directs the agent to paginate with "next_result_offset," a name that does not exist in the schema, where the pagination fields are result_offset and continuation_token — a misleading reference.

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 phrase "usage by first-level prefixes" largely restates the tool name, s3_prefix_usage, without defining what "usage" actually measures (storage bytes, object counts, request volume). It does hint at aggregation grouped by top-level prefixes, but there is no clear verb and no differentiation from siblings such as s3_largest_objects that also report size-oriented data.

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 choose this tool over the other thirteen s3_* siblings, nor any stated preconditions or exclusions. The only procedural hint is that aggregate rows are paginated, which is mechanics rather than routing context.

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 are absent, so the description carries the full burden, and it does disclose two real behaviors: the default expiry is 3600 seconds and the provider's maximum is unverified. What it omits is significant for a credential-issuing tool — that the returned URL grants temporary anonymous access, which credentials/permits are needed to sign, and whether the URL is reusable.

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 compact clause plus a semicolon-joined caveat; nothing is padded and the core action is front-loaded. It is terse to the point of under-specification, but that is a completeness problem rather than a verbosity one.

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 no annotations, no output schema, and 0% schema coverage, the description should carry more. It never states what is returned (a URL string), what expiry bounds are valid, or what permission the caller needs to sign the URL, so an agent cannot reliably invoke it without prior S3 knowledge.

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 4 parameters. The description supplies a default for expires_seconds (3600) that the schema does not encode, which is genuine added value, but bucket, key, and version_id receive no explanatory text anywhere, leaving the majority of parameters undocumented.

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 artifact: 'Create signed GET URL'. This clearly separates it from siblings like s3_get_object (which returns object bytes) and the many s3_list_* / s3_get_*_config tools. It stops short of naming the resource (an S3 object identified by bucket/key), so it isn't a 5.

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?

No guidance on when to use presigning versus just fetching the object with s3_get_object, nor any note about handing the URL to an external party or credential requirements. The agent must infer the use case entirely.

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?

With no annotations, the description carries the full behavioral burden. It discloses important traits such as the byte cap (65536) and partial-read behavior, and it mentions return content (detected type, CSV header). However, it omits read-only confirmation, permissions, side effects, error behavior, and rate/cost context.

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 wasted words. It is appropriately sized for the description's scope, even though the content itself is sparse.

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 tool with five parameters, no output schema, and no annotations, the description is too sparse. It gives some return information but omits parameter semantics, access requirements, and operational constraints, leaving an agent under-informed for correct invocation.

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 there are five parameters, yet the description explains none of them. It mentions '65536 bytes' and 'CSV header' but does not map these to max_bytes, encoding, bucket, key, or version_id, so it fails to compensate for the schema's lack of descriptions.

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 ('preview') and resource ('object' via name), plus the scope ('first at most 65536 bytes') and return content ('detected type and CSV header'). It is clear enough to distinguish it from full-object retrieval, but it does not explicitly name or route against siblings like s3_get_object or s3_head_object.

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?

No guidance is provided on when to use this tool versus s3_get_object, s3_head_object, or other siblings. The word 'preview' implies a use case, but there are no explicit conditions, exclusions, or alternatives stated.

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?

No annotations are supplied, so the description carries the full burden. It does disclose one meaningful behavior not present in the schema: the scan is 'bounded by max_scan', implying results may be truncated. It says nothing about read-only safety, permissions, or how partial results are signalled, which leaves real gaps for a 6-parameter 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 sentence with no filler, and the core scoping detail (older than N hours) is front-loaded. It is efficient, though arguably too terse for a six-parameter tool, which shows up as a completeness gap rather than verbosity.

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 no annotations, no output schema, and six parameters, the description should explain what is returned (list of uploads and which fields), how pagination via continuation_token works, and how this differs from s3_list_multipart_uploads. None of that is present, leaving the agent under-informed for a non-trivial tool.

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 compensate. It adds genuine meaning for the two least obvious parameters (older_than_hours default of 24, and max_scan as a scan bound), but leaves bucket, prefix, upload_id, and continuation_token entirely undocumented, so compensation is only partial.

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 'Find' plus 'uploads older than N hours' gives a rough idea, and the name says 'unfinished uploads', so the agent can infer this surfaces stale/incomplete multipart uploads. However, the description never actually says 'multipart' or what makes an upload 'unfinished', and it does not differentiate from the sibling s3_list_multipart_uploads, which appears to overlap.

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 not to use it, and no reference to the obvious alternative s3_list_multipart_uploads. The only contextual hint is the default threshold, which is a parameter detail rather than usage guidance.

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