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

No annotations provided, and description lacks details on side effects (e.g., duplicate behavior, permissions, return value). Only states the action without behavioral 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?

Single sentence that is concise and to the point. Could be slightly expanded for clarity, but no unnecessary words.

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 simple tool with one required param and no output schema, the description provides basic purpose but lacks operational completeness (e.g., error handling, idempotency).

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 only parameter 'name' has no description in schema (0% coverage) and the description does not add any constraints or format details (e.g., length, uniqueness).

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?

Clearly states verb 'Create', resource 'new custom folder', and location 'ePost Storage area'. Distinguishes from sibling tools like epost_move_to_folder and epost_list_storage.

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 this tool versus alternatives like epost_move_to_folder. No prerequisites (e.g., login required) or exclusions mentioned.

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, description must fully disclose behavior. 'DESTRUCTIVE' suggests irreversible but 'move to trash' implies reversible; ambiguous. Requires confirm:true but doesn't clarify side effects or permissions.

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 concise sentences, front-loaded with 'DESTRUCTIVE'. No wasted words.

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 or annotations; description omits whether deletion is reversible (sibling epost_restore_letter exists). Could explain restoration options or consequences.

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 has 0% description coverage; description only mentions 'confirm:true' without explaining the boolean's role or letter_id format. Fails to compensate for missing schema details.

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?

Clearly states the tool moves a letter to the trash, using 'DESTRUCTIVE' to indicate nature. Distinct from sibling epost_store_letter for archiving.

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?

Explicitly says to use for deletion and advises preferring epost_store_letter for archiving. Notes required confirm:true.

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 must carry the full burden. It only states the action and output but does not disclose behavioral traits such as whether it overwrites existing files, authentication requirements, rate limits, or error handling. This is insufficient for a bulk download operation.

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 that immediately states the action and return value. It is front-loaded and contains no unnecessary words, making it 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?

For a tool that downloads all letters, the description is too brief. It does not explain behavior on network failures, partial downloads, duplicate handling, or performance implications. No output schema exists to clarify the return value structure. Additional details are needed to ensure safe and effective use.

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 has no descriptions for the single parameter 'output_dir' (0% coverage). The description adds minimal meaning by mentioning 'to output_dir', but does not specify format, permissions, or how the directory is used. More detail is needed to compensate for the lack of schema 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?

The description clearly states the tool downloads every letter from the letterbox to a specified directory and returns the saved paths. The verb 'Download' and resource 'every letter' are specific, and it distinguishes from sibling tools like 'epost_download_letter' that handle single letters.

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 given on when to use this tool versus alternatives (e.g., epost_download_letter), or any prerequisites or limitations. The description lacks context for appropriate usage.

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 exist, and the description only mentions the return path format and a cryptic 'written 0600'. It does not disclose side effects, authentication needs, or error conditions, leaving the agent uninformed about important behavioral traits.

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 sentences with no extraneous words. The core action is front-loaded, and the return format is specified concisely.

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 the lack of annotations and output schema, the description is too minimal. It omits critical context like prerequisite steps (e.g., listing letters), error handling, and file overwrite behavior, making it insufficient for reliable agent use.

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 description adds minimal value beyond the schema: it explains that index and letter_id are alternatives, but does not describe the index's origin or format, and output_dir lacks any explanation. With only 33% schema coverage, the description fails to compensate adequately.

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 clearly states the tool downloads one letter to a specified directory, with two addressing methods (index or letter_id). It distinguishes itself from sibling tools like epost_download_all and epost_get_letter.

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 index vs letter_id, nor alternatives. No exclusionary context or when-not scenarios are provided.

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 must fully disclose behavior. It states 'Save' (a write operation) but omits details about file format, size limits, overwrite behavior, or authentication needs. Minimal transparency beyond the basic action.

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, concise and to the point. No unnecessary words, and it conveys the essential purpose.

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 no output schema, no annotations, and minimal parameter info, the description leaves many aspects unclear (e.g., return value, error handling). It is insufficient for an agent to fully understand the tool's behavior.

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 adds no explanation for the parameters 'letter_id' and 'output_path'. The names are somewhat self-explanatory, but the description should have clarified their purpose and format.

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 clearly states the verb ('Save') and the resource ('thumbnail image of a letter'). It also provides a use case that distinguishes it from siblings like 'epost_download_letter' (fetching full PDF).

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 clear context: 'useful to eyeball a document without fetching the whole PDF.' This implicitly suggests when to use it, but it does not explicitly exclude scenarios or name alternatives, though siblings list includes the full download tool.

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 full burden. It does not disclose behavioral traits like whether the operation is read-only, requires authentication, or has any side effects. The description only states what it returns, not how it behaves.

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, concise sentence (18 words) that efficiently communicates the core purpose. It earns its place with no superfluous information, though it could benefit from minor structuring (e.g., bullet points for included fields).

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 the tool has only one parameter and no output schema, the description is minimally adequate. It covers what the tool returns but does not explain the output structure, error handling, or relationship to other tools in the e-post system. For a simple retrieval tool, it meets basic needs but lacks completeness.

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?

With 0% schema description coverage, the description should explain the parameter. It only says 'its id' without clarifying the format, source, or constraints of the letter_id. The schema lists it as a required string with no description, so the tool adds little semantic value.

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 clearly states that the tool retrieves one letter by its ID, specifying the included details (sender description, document types, dates, read status). This distinguishes it from siblings like epost_list_letters which lists multiple letters.

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 explicit guidance on when to use this tool versus alternatives. The description does not mention prerequisites, such as needing the letter_id from another tool, nor does it advise against using it for bulk operations. Siblings exist (e.g., epost_search, epost_list_letters) but no comparison is provided.

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 bears full responsibility for behavioral disclosure. It reveals the output contains days remaining but omits any mention of authentication requirements, side effects, or pagination. This is insufficient for a tool expected to be invoked by an AI agent.

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 of 12 words with no redundancy. Every word contributes meaning, achieving maximum conciseness.

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 the tool has no parameters, no output schema, and no annotations, the description provides the core purpose but lacks details on sorting, scope (user-specific or global), or whether the list is exhaustive. It is minimally adequate but not fully 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?

There are zero parameters, and schema coverage is 100%, so the description adds value by explaining what the tool returns (deleted letters with days remaining). Baseline for zero parameters is 4, and the description fulfills that.

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 'Letters in the trash, with the days remaining before they are permanently removed' clearly indicates the tool lists deleted letters and shows retention time. It distinguishes from sibling tools like epost_list_letters (active letters) and epost_delete_letter (deletion action), though the verb is implied rather than explicit.

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 alternatives such as epost_list_letters or epost_restore_letter. The description gives no context for decision-making.

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 must fully disclose behavior. It mentions the limit behavior and fields returned, but does not explain pagination, authentication requirements, read-only nature, or whether it returns all letters (including read/unread).

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 two sentences long, front-loads the core purpose, and each sentence adds value. No unnecessary words.

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 description includes the fields returned and limit behavior, which is sufficient for a simple list tool. However, it could better differentiate from siblings by noting that it lists current (not deleted) letters.

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 100% with a description for the limit parameter. The description adds a note about the limit behavior, which adds slight context but does not significantly improve upon the schema.

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 clearly states the action 'List' and the resource 'letters currently in the digital letterbox', and lists the returned fields. This distinguishes it from siblings like epost_list_deleted and epost_search.

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 mentions the limit behavior but does not explicitly state when to use this tool versus alternatives like epost_search or epost_list_deleted. No exclusion criteria or typical use cases are provided.

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, but the description transparently indicates a read-only listing operation with no side effects. It accurately describes the output (folder names, document counts) without contradicting any structured data.

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 that conveys all necessary information without redundancy. It is front-loaded with the main action and specific details, making it efficient and easy to parse.

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 no output schema, the description fully explains what the tool returns: custom folders with name and document count, plus the unsorted My-Documents count. This is sufficient for an agent to understand the tool's output without additional context.

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 input schema has no parameters, so the description cannot add parameter meaning beyond what exists. Baseline of 4 is appropriate as there is nothing to document.

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 explicitly states the tool lists custom folders with name and document count, plus the My-Documents count. It uses specific verbs ('list') and resources ('custom folders', 'My-Documents count'), making the purpose clear and distinct from generic listing.

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 explicit guidance on when to use this tool versus alternatives like epost_list_storage_documents or epost_list_letters. However, the sibling list suggests a potential distinction between listing storage structure vs. content, but this is not 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 exist, so the description carries full burden. It reveals behavioral differences between API and browser fallback (descriptions vs. date/tag). However, it does not state read-only nature, permissions, or pagination/limits. Adds some value but missing depth.

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 sentences, front-loaded with purpose, no redundancy. Could be more structured by explicitly listing parameters, but it is concise and readable.

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 three parameters and no output schema or annotations, the description omits default behavior (listing all documents when folder_id omitted) and does not explain the limit parameter's purpose. The distinction between API and browser fallback is helpful but incomplete.

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 67%. The description adds meaning for folder_id and scroll_all beyond schema, but limit (missing schema description) remains unexplained. Two of three parameters benefit; one is overlooked.

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 clearly states the tool lists documents in Storage, with a specific verb and resource. It distinguishes between API and browser fallback behaviors but does not explicitly differentiate from sibling tools like epost_list_storage or epost_list_letters.

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 provides parameter-level guidance (use folder_id for one folder, scroll_all for browser path) but lacks high-level when-to-use advice compared to siblings like epost_search or epost_list_storage.

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?

The description discloses key behaviors: visible browser, credential filling, passkey request, manual fallback, session caching. Without annotations, it provides sufficient transparency. It does not mention potential side effects like leaving the browser open, but the wait_seconds parameter mitigates this.

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 mostly concise, packing all essential information into two sentences. The first sentence is slightly long but front-loads the main action. No extraneous 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?

Given the complexity of a login automation tool with multiple steps (browser, credentials, fallback, caching), the description covers all aspects sufficiently. No output schema is needed, and the parameter is well-documented.

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 100%, and the parameter description in the schema already explains wait_seconds. The tool description adds value by explaining the reason for the minimum (SwissID redirect chain), which aids agent understanding.

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 clearly states the tool automates SwissID login by opening a visible browser, filling email, requesting passkey, and handling fallback. It distinguishes itself from sibling tools (which are post-login operations) and uses specific verbs like 'open' and 'drive'.

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 implicitly indicates when to use (automating login except biometric prompt) and mentions fallback behavior. It lacks an explicit statement of when not to use (e.g., if manual login is preferred), but the context among siblings makes the usage clear.

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 provided, the description fully discloses behavioral traits: idempotent (no-op if already filed), adds folder membership without removal unless remove_from is specified, and notes the side effect of bumping the document's position. No contradictions with structured data.

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 paragraph that front-loads the main action and gradually provides details. At about 100 words, it is fairly concise, though some phrasing like 'unticked in the same sheet' could be simplified. Overall, every sentence adds value without redundancy.

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 the tool is a mutation with no output schema, the description covers the core behavior, parameters, and side effects. It doesn't detail return values or error scenarios, but that is acceptable. The sibling list provides context for when this tool is appropriate.

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 only 25% (only remove_from has a description), so the description carries the burden. It explains the meaning of all four parameters: index as position in list, title as substring, folder as target, remove_from as old folder to drop. This compensates well for the lack of schema 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?

The description clearly states it files a Storage document into a custom folder, specifying the action, resource, and method of addressing (by index or substring). It distinguishes itself from sibling tools like epost_create_folder and epost_unfile_from_folder by explaining it adds membership and is idempotent.

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 concrete usage context: how to address (index or substring), how to re-file using remove_from, and notes that filing bumps the document to top of 'Last used' order, requiring re-listing before next index. However, it does not explicitly state when not to use this tool or suggest alternatives beyond the sibling list.

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 provided, so description carries full burden. It describes the tool as reading/reporting information, implying read-only, but does not explicitly state side effects, permissions, or rate limits. The optional PDF saving is a side effect noted.

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 efficient sentences: first states core function and outputs, second explains rationale and optional parameter. No wasted words.

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?

Despite good purpose clarity, the description lacks parameter usage guidance, return format, and explicit behavioral traits. For a tool with 5 undocumented parameters and no output schema, more detail is needed to be 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 coverage is 20% (only output_dir described). Description adds no guidance on how to identify the document (index, title, folder_id, letter_id are unexplained). It only repeats the output_dir purpose.

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?

Description clearly states it opens a storage document and reports specific fields (sender, subject, type, date, amount, folder). It distinguishes from siblings by noting the card list only shows 'Gescannter Brief' and this tool is the only way to classify archived documents.

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?

Description implies when to use (to classify archived documents) by stating it's the only way. It mentions the optional output_dir parameter for saving PDF, but does not explicitly state when not to use or compare alternatives.

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 must disclose behavioral traits. It only says 'restore' but doesn't specify side effects, what happens if the letter_id is invalid or already restored, or any state changes. The description is insufficient for safe usage.

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, which is concise, but it is too minimal to provide sufficient value. It is not verbose, but could be structured to include more context without losing conciseness.

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 simple tool with one parameter and no output schema, the description should adequately cover behavior. However, it lacks information on return values, error cases, and prerequisites, making it incomplete for an AI agent to invoke reliably.

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 sole parameter 'letter_id' is not explained beyond the schema. With 0% schema description coverage, the description should have added meaning, such as what format the ID is or how to obtain it. No extra semantics provided.

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 clearly states the action (restore) and resource (deleted letter) and specifies the target location (inbox). It distinguishes itself from sibling tools like epost_delete_letter and epost_list_deleted.

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 this tool compared to siblings. For example, it doesn't mention prerequisites like the letter must be deleted first, or that it's the inverse of epost_delete_letter. The description lacks usage 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?

No annotations are provided, so the description must cover behavioral traits. It describes the search behavior and optional location filtering, but doesn't mention whether it's read-only, pagination, or any side effects.

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 concise sentences that front-load the purpose and add essential detail about scope and API-only nature, with no wasted words.

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 3-parameter tool with no output schema, the description covers the core search functionality and optional filters. Could mention return format, but overall adequate.

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 only 33% (location has description). The description adds value by clarifying keyword matches content (vs metadata) and location limits to inbox/storage, but doesn't explain the limit parameter.

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 clearly states the tool does full-text search across letters, matching keywords in content rather than metadata, which is specific and distinguishes it from other listing tools.

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 mentions 'API only; no equivalent in portal automation', giving context that it's an API-specific operation. However, it doesn't explicitly state when to use this versus sibling tools like epost_list_letters.

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 provided, so the description carries full burden. It states the tool marks letters read/unread, implying state change, but does not disclose side effects, required permissions, rate limits, or behavior for non-existent letters.

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 sentence of 5 words, highly concise and front-loaded. Lacks structured details but achieves brevity without wasted words.

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 output schema, no annotations, and 2 parameters, the description is too minimal. It does not explain return behavior, error conditions, or what happens on success/failure. Incomplete for a mutation 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%. The description adds no meaning beyond the schema: 'by id' is redundant with the 'letter_ids' parameter. The 'status' parameter is only defined by its enum values in the schema.

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 'Mark letters READ or UNREAD by id.' clearly states the action (mark), the resource (letters), and the specific states (READ/UNREAD). It distinguishes this tool from siblings like epost_unread_count (count only) and epost_status (likely different).

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 usage guidelines provided. The description does not indicate when to use this tool versus alternatives, nor does it mention prerequisites (e.g., login required) or context for setting read vs unread status.

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 full burden. It discloses what information is shown but does not explicitly state it is read-only or mention any side effects, authentication needs, or rate limits. The description is adequate but could be improved.

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, concise and well-structured, front-loading the purpose and listing specifics without extraneous words.

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 no output schema, the description should compensate. It lists the types of information but does not specify the output format or structure, leaving some uncertainty. For a simple info tool, it is partially 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?

With zero parameters and 100% schema coverage, the description adds meaning by explaining what the tool outputs. Baseline is 4, and the description provides clear detail on the configuration fields, earning a 5.

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 clearly states the tool shows the resolved configuration and lists specific items like browser driver, Touch ID capability, paths, and email config. It is distinct from sibling tools which perform actions like login or list letters.

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 explicit guidance on when or when not to use this tool. It is implied for configuration inspection, but no alternatives or prerequisites are mentioned.

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 full burden. It discloses the return values ('ok' or 'login_required') and implies a read-only operation, but does not explicitly state it is non-destructive or idempotent. Additional context like 'This operation does not modify any data' would improve transparency.

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 of 16 words, front-loading the purpose. Every word is meaningful with no redundancy or 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?

For a simple status-check tool with no parameters and no output schema, the description is complete. It explains what the tool checks and the two possible return values, sufficient for an agent to understand its behavior.

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 has no parameters (empty input schema, 100% coverage). Per scoring rules, baseline is 4 for zero parameters. The description adds no parameter information, which is acceptable given no parameters exist.

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 clearly states the tool checks ePost session status, returning 'ok' or 'login_required'. It specifies the resource (ePost session) and the action (check), distinguishing it from sibling tools like epost_login or epost_unread_count.

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 provides no guidance on when to use this tool versus alternatives, such as suggesting it be called before other ePost operations to verify session validity. There is no mention of prerequisites or exclusions.

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 full behavioral burden. It discloses the action is non-destructive, requires a folder, and addresses methods with index shift warning. Lacks details on permissions, error handling, or side effects, but adequate for a simple archival action.

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 sentences with no redundancy. Front-loaded with core action and key differentiator (not a delete). Every sentence adds value.

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 no output schema and 4 parameters (1 required), the description covers the main behavior, identification methods, and a crucial behavioral warning (index shift). Could mention error handling or what happens if letter not found, but overall complete for intended use.

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?

Adds meaningful context beyond the input schema: clarifies that folder is required, explains how to identify letters via index or title substring, and notes indices shift. The schema covers 50% of parameters; description compensates well.

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?

Clearly states it archives a letter into a Storage folder (the 'Store' action), emphasizes it is not a delete, and distinguishes from sibling tools like epost_delete_letter.

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 clear instructions on how to address a letter (by index or substring) and warns that indices shift after each store, recommending re-listing. Does not explicitly state when not to use or compare to alternatives, but context is sufficient.

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 provided, so description fully responsible. It discloses the core operation and the limitation about empty folder sets. However, it does not mention side effects, success behavior, or permissions needed. Some behavioral gaps remain.

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 concise sentences, front-loaded with the core purpose, followed by a necessary note. No redundant or irrelevant 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?

Given no annotations or output schema, the description fails to explain parameter semantics, leaving uncertainty about how to specify the document. The alternative tool mention helps, but overall completeness is moderate.

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%, yet the description explains none of the three parameters (index, title, folder). The folder parameter is implied but not clarified. The agent cannot determine how to identify the document (by index, title, or both).

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?

Clearly states 'Remove a Storage document from a folder,' using a specific verb and resource. The note distinguishes from the sibling tool epost_move_to_folder by explaining when to use which, providing clear 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?

Explicitly states when the tool works (document in more than one folder) and when not (single folder membership). Provides an explicit alternative: use epost_move_to_folder with remove_from instead.

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 bears the full burden of behavioral disclosure. However, it only states the tool returns a count, with no mention of authentication requirements, side effects, rate limits, or the format of the return value. For a read operation, these details are missing.

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, front-loaded, and contains no superfluous words. It could benefit from adding brief context without becoming verbose, but it achieves efficient communication of the core purpose.

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 output schema and no annotations, the description is the sole source of information. It fails to specify what format the count is returned in, whether it requires being logged in (sibling epost_login suggests authentication), and if it's scoped to the current user. This lack of completeness could confuse an AI agent.

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?

There are no parameters, so schema coverage is trivially 100%. The description does not need to add parameter meaning, but it also does not explain what the tool returns or how to interpret the result. Baseline 3 is appropriate.

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 clearly states the tool returns the count of unread letters in the inbox. It uses a specific resource (unread letters) and scope (inbox), and implicitly distinguishes itself from sibling tools like epost_list_letters which list the actual letters.

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 alternatives. For example, it does not mention that for detailed unread letter info, one should use epost_list_letters with a filter. The description gives no when-not or alternative suggestions.

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